< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 5102 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6812. Min Act: -0.1700

Data Index: 7093895 (Open Web Text)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6343. Min Act: -0.1700

Data Index: 2243251 (Open Web Text)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5717. Min Act: -0.1700

Data Index: 8526023 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5873. Min Act: -0.1700

Data Index: 1944839 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5560. Min Act: -0.1700

Data Index: 2885182 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5403. Min Act: -0.1700

Data Index: 602189 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5090. Min Act: -0.1700

Data Index: 4581303 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4777. Min Act: -0.1700

Data Index: 5236415 (Open Web Text)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4934. Min Act: -0.1700

Data Index: 2876982 (Open Web Text)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4777. Min Act: -0.1700

Data Index: 3002364 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4620. Min Act: -0.1700

Data Index: 4705537 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4464. Min Act: -0.1700

Data Index: 7780951 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4464. Min Act: -0.1700

Data Index: 7882276 (Open Web Text)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4464. Min Act: -0.1700

Data Index: 3863122 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4307. Min Act: -0.1700

Data Index: 2962774 (Open Web Text)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.3837. Min Act: -0.1700

Data Index: 134155 (Open Web Text)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.3837. Min Act: -0.1700

Data Index: 6747084 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.3680. Min Act: -0.1700

Data Index: 1306682 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.3366. Min Act: -0.1700

Data Index: 1131349 (Open Web Text)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.3366. Min Act: -0.1700

Data Index: 4727243 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #19