Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.4319. Min Act: -0.1700

Data Index: 4348392 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.3965. Min Act: -0.1700

Data Index: 2094250 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.2935. Min Act: -0.1700

Data Index: 3623974 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.2796. Min Act: -0.1700

Data Index: 7526183 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.2385. Min Act: -0.1700

Data Index: 4373265 (Open Web Text)

Max Activating Token Index: 331

Text #5

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.2059. Min Act: -0.1700

Data Index: 3327163 (Open Web Text)

Max Activating Token Index: 363

Text #6

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.2383. Min Act: -0.1700

Data Index: 7799069 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.1915. Min Act: -0.1700

Data Index: 2391871 (Open Web Text)

Max Activating Token Index: 382

Text #8

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.1524. Min Act: -0.1700

Data Index: 1441866 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.1166. Min Act: -0.1700

Data Index: 491255 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0806. Min Act: -0.1700

Data Index: 8389354 (Open Web Text)

Max Activating Token Index: 552

Text #11

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0869. Min Act: -0.1700

Data Index: 4009375 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0943. Min Act: -0.1700

Data Index: 6561377 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0989. Min Act: -0.1700

Data Index: 595769 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0856. Min Act: -0.1700

Data Index: 5817815 (Open Web Text)

Max Activating Token Index: 750

Text #15

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0838. Min Act: -0.1700

Data Index: 5431876 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0467. Min Act: -0.1700

Data Index: 824297 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0674. Min Act: -0.1700

Data Index: 6550263 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0802. Min Act: -0.1700

Data Index: 418313 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 4.4319. Min Range: -4.4319

Max Act: 4.0705. Min Act: -0.1700

Data Index: 7888212 (Open Web Text)

Max Activating Token Index: 460