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

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

Neuron 3329 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1105336 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 598123 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0165. Min Act: -0.0003

Data Index: 486435 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0165. Min Act: -0.0003

Data Index: 113079 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 941304 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1009365 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 521446 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0003

Data Index: 897856 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0003

Data Index: 574470 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0002

Data Index: 174123 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0003

Data Index: 418645 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1090714 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0003

Data Index: 201388 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0003

Data Index: 853096 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0003

Data Index: 512478 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0003

Data Index: 427617 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1065891 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1189407 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1076268 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1159156 (C4 (Web Text))

Max Activating Token Index: 250