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

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

Neuron 430 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0003

Data Index: 67638 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0004

Data Index: 705930 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1098911 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0186. Min Act: -0.0004

Data Index: 1178462 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0184. Min Act: -0.0004

Data Index: 169464 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0180. Min Act: -0.0003

Data Index: 225566 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0180. Min Act: -0.0003

Data Index: 165807 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0168. Min Act: -0.0003

Data Index: 320440 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0171. Min Act: -0.0004

Data Index: 424741 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0170. Min Act: -0.0004

Data Index: 134671 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1233432 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0165. Min Act: -0.0004

Data Index: 466302 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0169. Min Act: -0.0003

Data Index: 593881 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1176264 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1255832 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1124846 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1106922 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0003

Data Index: 587271 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0161. Min Act: -0.0004

Data Index: 473509 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0161. Min Act: -0.0004

Data Index: 359463 (C4 (Web Text))

Max Activating Token Index: 913