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

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

Neuron 1452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0006

Data Index: 186163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0164. Min Act: -0.0006

Data Index: 243975 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0179. Min Act: -0.0006

Data Index: 455327 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0163. Min Act: -0.0006

Data Index: 406424 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0165. Min Act: -0.0006

Data Index: 828064 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0166. Min Act: -0.0006

Data Index: 665952 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0163. Min Act: -0.0006

Data Index: 566067 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0144. Min Act: -0.0006

Data Index: 852118 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1274449 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1260819 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1019759 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0144. Min Act: -0.0006

Data Index: 88851 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0146. Min Act: -0.0006

Data Index: 427353 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1166504 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0136. Min Act: -0.0006

Data Index: 816720 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0147. Min Act: -0.0006

Data Index: 770616 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0150. Min Act: -0.0006

Data Index: 102281 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0139. Min Act: -0.0006

Data Index: 560469 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0129. Min Act: -0.0006

Data Index: 315206 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0138. Min Act: -0.0006

Data Index: 348419 (C4 (Web Text))

Max Activating Token Index: 645