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

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

Neuron 1335 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: 0.0202. Min Range: -0.0202

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1042389 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1163066 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0173. Min Act: -0.0003

Data Index: 428899 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0166. Min Act: -0.0003

Data Index: 854916 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0166. Min Act: -0.0003

Data Index: 927958 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0144. Min Act: -0.0003

Data Index: 413180 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0003

Data Index: 697035 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1073050 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1246938 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0161. Min Act: -0.0003

Data Index: 368558 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0156. Min Act: -0.0003

Data Index: 435286 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1324753 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0149. Min Act: -0.0003

Data Index: 855982 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1197540 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1323700 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0149. Min Act: -0.0003

Data Index: 589590 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0135. Min Act: -0.0003

Data Index: 931349 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0144. Min Act: -0.0003

Data Index: 711465 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0151. Min Act: -0.0004

Data Index: 984594 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0137. Min Act: -0.0003

Data Index: 503149 (C4 (Web Text))

Max Activating Token Index: 781