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

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

Neuron 961 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: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0003

Data Index: 169627 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0178. Min Act: -0.0003

Data Index: 88736 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0174. Min Act: -0.0004

Data Index: 319641 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0173. Min Act: -0.0003

Data Index: 335359 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0178. Min Act: -0.0003

Data Index: 799749 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0170. Min Act: -0.0003

Data Index: 293421 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0171. Min Act: -0.0003

Data Index: 937701 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0170. Min Act: -0.0003

Data Index: 946492 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0166. Min Act: -0.0003

Data Index: 939775 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0169. Min Act: -0.0004

Data Index: 344280 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1234203 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1488253 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0152. Min Act: -0.0003

Data Index: 788208 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1467226 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0175. Min Act: -0.0003

Data Index: 38099 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0168. Min Act: -0.0003

Data Index: 513313 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0156. Min Act: -0.0003

Data Index: 298731 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0162. Min Act: -0.0003

Data Index: 644641 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1490242 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1529337 (Python Code)

Max Activating Token Index: 496