Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2802 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0003

Data Index: 23398 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0187. Min Act: -0.0003

Data Index: 338485 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0156. Min Act: -0.0003

Data Index: 259638 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0165. Min Act: -0.0004

Data Index: 1145648 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0168. Min Act: -0.0003

Data Index: 694956 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0156. Min Act: -0.0003

Data Index: 634970 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1138058 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1301866 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0148. Min Act: -0.0003

Data Index: 208588 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1181842 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0149. Min Act: -0.0003

Data Index: 68167 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1656908 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1078721 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1176647 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0003

Data Index: 417387 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0151. Min Act: -0.0003

Data Index: 476640 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0148. Min Act: -0.0003

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0137. Min Act: -0.0004

Data Index: 1479296 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0152. Min Act: -0.0003

Data Index: 781670 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1622300 (Python Code)

Max Activating Token Index: 246