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

Dataset: Open Web Text

Neuron 2435 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: 3.5384. Min Range: -3.5384

Max Act: 3.5384. Min Act: -0.1700

Data Index: 5852040 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1386141 (Open Web Text)

Max Activating Token Index: 849

Text #2

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4574. Min Act: -0.1700

Data Index: 4378856 (Open Web Text)

Max Activating Token Index: 313

Text #3

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4237. Min Act: -0.1700

Data Index: 8406934 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4285. Min Act: -0.1700

Data Index: 3467660 (Open Web Text)

Max Activating Token Index: 145

Text #5

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4273. Min Act: -0.1700

Data Index: 1366772 (Open Web Text)

Max Activating Token Index: 217

Text #6

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4375. Min Act: -0.1700

Data Index: 318642 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4166. Min Act: -0.1700

Data Index: 6174124 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4211. Min Act: -0.1700

Data Index: 5808726 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4187. Min Act: -0.1700

Data Index: 1645910 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4299. Min Act: -0.1700

Data Index: 3928075 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3775. Min Act: -0.1700

Data Index: 2135373 (Open Web Text)

Max Activating Token Index: 579

Text #12

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3917. Min Act: -0.1700

Data Index: 1383444 (Open Web Text)

Max Activating Token Index: 199

Text #13

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4038. Min Act: -0.1700

Data Index: 8150783 (Open Web Text)

Max Activating Token Index: 94

Text #14

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3865. Min Act: -0.1700

Data Index: 525641 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.4114. Min Act: -0.1700

Data Index: 6139813 (Open Web Text)

Max Activating Token Index: 92

Text #16

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3834. Min Act: -0.1700

Data Index: 4476191 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3913. Min Act: -0.1700

Data Index: 5449639 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3786. Min Act: -0.1700

Data Index: 6125570 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 3.5384. Min Range: -3.5384

Max Act: 3.3831. Min Act: -0.1700

Data Index: 7953635 (Open Web Text)

Max Activating Token Index: 486