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

Dataset: Open Web Text

Neuron 2141 in Layer 3

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: 3.7194. Min Range: -3.7194

Max Act: 3.7028. Min Act: -0.1700

Data Index: 5259 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.7194. Min Act: -0.1700

Data Index: 4643792 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6574. Min Act: -0.1700

Data Index: 3372412 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6087. Min Act: -0.1700

Data Index: 5455339 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5770. Min Act: -0.1700

Data Index: 7711839 (Open Web Text)

Max Activating Token Index: 509

Text #5

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6075. Min Act: -0.1700

Data Index: 4912638 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6216. Min Act: -0.1700

Data Index: 3023685 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5959. Min Act: -0.1700

Data Index: 6358108 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1672933 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.6089. Min Act: -0.1700

Data Index: 5755842 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5515. Min Act: -0.1700

Data Index: 5173914 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5712. Min Act: -0.1700

Data Index: 1314825 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5082. Min Act: -0.1700

Data Index: 708442 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5180. Min Act: -0.1700

Data Index: 7613930 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5697. Min Act: -0.1700

Data Index: 1926259 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5639. Min Act: -0.1700

Data Index: 196992 (Open Web Text)

Max Activating Token Index: 809

Text #16

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5274. Min Act: -0.1700

Data Index: 4476005 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5464. Min Act: -0.1700

Data Index: 7645163 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5697. Min Act: -0.1700

Data Index: 4536442 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5370. Min Act: -0.1700

Data Index: 5729334 (Open Web Text)

Max Activating Token Index: 267