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

Dataset: Open Web Text

Neuron 58 in Layer 4

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: 2.7207. Min Range: -2.7207

Max Act: 2.7207. Min Act: -0.1700

Data Index: 3737175 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.6549. Min Act: -0.1700

Data Index: 2081853 (Open Web Text)

Max Activating Token Index: 300

Text #2

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.6389. Min Act: -0.1700

Data Index: 5568272 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.6335. Min Act: -0.1700

Data Index: 5953868 (Open Web Text)

Max Activating Token Index: 323

Text #4

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.6121. Min Act: -0.1700

Data Index: 488332 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.6142. Min Act: -0.1700

Data Index: 7944001 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5851. Min Act: -0.1700

Data Index: 4663018 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5745. Min Act: -0.1700

Data Index: 3058642 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5695. Min Act: -0.1700

Data Index: 8256748 (Open Web Text)

Max Activating Token Index: 81

Text #9

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5765. Min Act: -0.1700

Data Index: 2287836 (Open Web Text)

Max Activating Token Index: 498

Text #10

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5714. Min Act: -0.1700

Data Index: 6831723 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5570. Min Act: -0.1700

Data Index: 4768241 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5577. Min Act: -0.1700

Data Index: 5052501 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5638. Min Act: -0.1700

Data Index: 5009785 (Open Web Text)

Max Activating Token Index: 544

Text #14

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5439. Min Act: -0.1700

Data Index: 2256636 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5480. Min Act: -0.1700

Data Index: 7494359 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5293. Min Act: -0.1700

Data Index: 7611674 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5446. Min Act: -0.1700

Data Index: 4155715 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5435. Min Act: -0.1700

Data Index: 2405075 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.7207. Min Range: -2.7207

Max Act: 2.5302. Min Act: -0.1700

Data Index: 2564237 (Open Web Text)

Max Activating Token Index: 92