Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1669 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0006

Data Index: 333140 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0169. Min Act: -0.0006

Data Index: 295749 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1173992 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0168. Min Act: -0.0006

Data Index: 744970 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1167853 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0170. Min Act: -0.0006

Data Index: 658370 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0166. Min Act: -0.0006

Data Index: 642100 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0159. Min Act: -0.0006

Data Index: 547683 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0160. Min Act: -0.0006

Data Index: 575423 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0164. Min Act: -0.0006

Data Index: 313260 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0164. Min Act: -0.0006

Data Index: 329067 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1070696 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1026003 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1220525 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0162. Min Act: -0.0006

Data Index: 836846 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0162. Min Act: -0.0006

Data Index: 721254 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0162. Min Act: -0.0006

Data Index: 53597 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0165. Min Act: -0.0006

Data Index: 220814 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0161. Min Act: -0.0006

Data Index: 454174 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0161. Min Act: -0.0006

Data Index: 339653 (C4 (Web Text))

Max Activating Token Index: 935