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

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

Neuron 507 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0167. Min Act: -0.0005

Data Index: 356060 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0005

Data Index: 689903 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0005

Data Index: 620879 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0006

Data Index: 422812 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1005472 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1185257 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0160. Min Act: -0.0006

Data Index: 367695 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0160. Min Act: -0.0006

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0159. Min Act: -0.0006

Data Index: 956762 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0005

Data Index: 764694 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0156. Min Act: -0.0006

Data Index: 440255 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0158. Min Act: -0.0006

Data Index: 241941 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0157. Min Act: -0.0006

Data Index: 680606 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0006

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1187872 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1122409 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1202583 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1164148 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0156. Min Act: -0.0006

Data Index: 959713 (C4 (Web Text))

Max Activating Token Index: 441