Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1051831 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0185. Min Act: -0.0003

Data Index: 514161 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0003

Data Index: 203370 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0141. Min Act: -0.0003

Data Index: 125604 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1150257 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0166. Min Act: -0.0003

Data Index: 136040 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0172. Min Act: -0.0003

Data Index: 604869 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0145. Min Act: -0.0003

Data Index: 972544 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1224205 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0155. Min Act: -0.0003

Data Index: 957762 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0191. Min Act: -0.0003

Data Index: 944328 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0149. Min Act: -0.0003

Data Index: 447072 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0135. Min Act: -0.0003

Data Index: 789341 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0145. Min Act: -0.0003

Data Index: 556821 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1264193 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0145. Min Act: -0.0003

Data Index: 212062 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1302188 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1182955 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0134. Min Act: -0.0003

Data Index: 662383 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0137. Min Act: -0.0003

Data Index: 76992 (C4 (Web Text))

Max Activating Token Index: 97