< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 34 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6826. Min Act: -0.1700

Data Index: 7916387 (Open Web Text)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6739. Min Act: -0.1700

Data Index: 3561847 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6478. Min Act: -0.1700

Data Index: 1035833 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6478. Min Act: -0.1700

Data Index: 7820301 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6217. Min Act: -0.1699

Data Index: 6498215 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6304. Min Act: -0.1700

Data Index: 6074296 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6217. Min Act: -0.1700

Data Index: 4400240 (Open Web Text)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6042. Min Act: -0.1700

Data Index: 7820299 (Open Web Text)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6042. Min Act: -0.1700

Data Index: 6524850 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6042. Min Act: -0.1700

Data Index: 8479414 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6130. Min Act: -0.1700

Data Index: 22768 (Open Web Text)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6042. Min Act: -0.1700

Data Index: 1627325 (Open Web Text)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5955. Min Act: -0.1700

Data Index: 7916381 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6042. Min Act: -0.1700

Data Index: 93417 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5955. Min Act: -0.1700

Data Index: 128689 (Open Web Text)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5780. Min Act: -0.1700

Data Index: 3962424 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5868. Min Act: -0.1700

Data Index: 1097743 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5780. Min Act: -0.1700

Data Index: 8770018 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5693. Min Act: -0.1700

Data Index: 6971482 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5605. Min Act: -0.1700

Data Index: 817419 (Open Web Text)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #19