Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3358 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0002

Data Index: 310580 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0163. Min Act: -0.0002

Data Index: 597016 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0152. Min Act: -0.0002

Data Index: 717355 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0154. Min Act: -0.0002

Data Index: 539286 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0143. Min Act: -0.0002

Data Index: 239620 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0139. Min Act: -0.0002

Data Index: 786791 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0143. Min Act: -0.0002

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0134. Min Act: -0.0002

Data Index: 835865 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1269830 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0002

Data Index: 696624 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0132. Min Act: -0.0002

Data Index: 885622 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1146160 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0135. Min Act: -0.0002

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1225997 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0002

Data Index: 290859 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0134. Min Act: -0.0002

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0128. Min Act: -0.0002

Data Index: 715713 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1212476 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1226180 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0133. Min Act: -0.0002

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 700