< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 55 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.8959. Min Act: -0.1700

Data Index: 7627844 (Open Web Text)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.7084. Min Act: -0.1700

Data Index: 4450992 (Open Web Text)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.5209. Min Act: -0.1700

Data Index: 6833792 (Open Web Text)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.4584. Min Act: -0.1700

Data Index: 1496332 (Open Web Text)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.4584. Min Act: -0.1700

Data Index: 530933 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.4584. Min Act: -0.1700

Data Index: 7503326 (Open Web Text)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.3334. Min Act: -0.1700

Data Index: 1113847 (Open Web Text)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.3334. Min Act: -0.1700

Data Index: 6483134 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.3334. Min Act: -0.1700

Data Index: 6790036 (Open Web Text)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.2709. Min Act: -0.1700

Data Index: 6215371 (Open Web Text)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.2709. Min Act: -0.1700

Data Index: 4512757 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.2084. Min Act: -0.1700

Data Index: 2434332 (Open Web Text)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.2084. Min Act: -0.1700

Data Index: 4420397 (Open Web Text)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.1459. Min Act: -0.1700

Data Index: 4034266 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.1459. Min Act: -0.1700

Data Index: 6435914 (Open Web Text)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.1459. Min Act: -0.1700

Data Index: 5513391 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.1459. Min Act: -0.1700

Data Index: 506235 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.1459. Min Act: -0.1700

Data Index: 328781 (Open Web Text)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.0834. Min Act: -0.1700

Data Index: 102236 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.8959. Min Range: -10.8959

Max Act: 10.0834. Min Act: -0.1700

Data Index: 3910751 (Open Web Text)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #19