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

Dataset: Open Web Text

Neuron 162 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: 3.1196. Min Range: -3.1196

Max Act: 3.1083. Min Act: -0.1700

Data Index: 2085717 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.1172. Min Act: -0.1700

Data Index: 5713386 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.1196. Min Act: -0.1700

Data Index: 7765102 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0563. Min Act: -0.1700

Data Index: 8044332 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0376. Min Act: -0.1700

Data Index: 2190945 (Open Web Text)

Max Activating Token Index: 180

Text #5

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0115. Min Act: -0.1700

Data Index: 5391011 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0342. Min Act: -0.1700

Data Index: 1707729 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0177. Min Act: -0.1700

Data Index: 4043912 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0341. Min Act: -0.1700

Data Index: 2675964 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0247. Min Act: -0.1700

Data Index: 3262701 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0142. Min Act: -0.1700

Data Index: 1239062 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0227. Min Act: -0.1700

Data Index: 6730212 (Open Web Text)

Max Activating Token Index: 398

Text #12

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0116. Min Act: -0.1700

Data Index: 123548 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0143. Min Act: -0.1700

Data Index: 3505007 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 3.1196. Min Range: -3.1196

Max Act: 2.9938. Min Act: -0.1700

Data Index: 3771183 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 3.1196. Min Range: -3.1196

Max Act: 2.9950. Min Act: -0.1700

Data Index: 7536738 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 3.1196. Min Range: -3.1196

Max Act: 2.9831. Min Act: -0.1700

Data Index: 687843 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 3.1196. Min Range: -3.1196

Max Act: 3.0178. Min Act: -0.1700

Data Index: 708981 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 3.1196. Min Range: -3.1196

Max Act: 2.9934. Min Act: -0.1700

Data Index: 3697953 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 3.1196. Min Range: -3.1196

Max Act: 2.9974. Min Act: -0.1700

Data Index: 8044333 (Open Web Text)

Max Activating Token Index: 703