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

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

Neuron 897 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0003

Data Index: 538942 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0003

Data Index: 564043 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1239248 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0172. Min Act: -0.0003

Data Index: 67936 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0003

Data Index: 919760 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0003

Data Index: 365622 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0157. Min Act: -0.0003

Data Index: 407310 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1033743 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1024157 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0139. Min Act: -0.0003

Data Index: 969533 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0140. Min Act: -0.0003

Data Index: 859797 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1140776 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0136. Min Act: -0.0003

Data Index: 962581 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0002

Data Index: 240944 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0002

Data Index: 620864 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1641290 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1136486 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1181715 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0127. Min Act: -0.0003

Data Index: 313972 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0135. Min Act: -0.0003

Data Index: 849105 (C4 (Web Text))

Max Activating Token Index: 516