Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2923 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0003

Data Index: 524614 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1346955 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0183. Min Act: -0.0003

Data Index: 229709 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0180. Min Act: -0.0003

Data Index: 140213 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0175. Min Act: -0.0003

Data Index: 48637 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0174. Min Act: -0.0003

Data Index: 568818 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0173. Min Act: -0.0003

Data Index: 704576 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0168. Min Act: -0.0003

Data Index: 691826 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1350644 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1253168 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0167. Min Act: -0.0003

Data Index: 302458 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0170. Min Act: -0.0003

Data Index: 599963 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0166. Min Act: -0.0003

Data Index: 116229 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1238312 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0160. Min Act: -0.0003

Data Index: 736583 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0159. Min Act: -0.0003

Data Index: 990138 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0160. Min Act: -0.0003

Data Index: 465526 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0160. Min Act: -0.0003

Data Index: 748455 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0159. Min Act: -0.0003

Data Index: 925441 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1132227 (C4 (Web Text))

Max Activating Token Index: 928