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

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

Neuron 804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0003

Data Index: 450946 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0003

Data Index: 854648 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0155. Min Act: -0.0003

Data Index: 899964 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1057911 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0144. Min Act: -0.0003

Data Index: 908357 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0145. Min Act: -0.0003

Data Index: 490968 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1018455 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1128898 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0143. Min Act: -0.0003

Data Index: 289145 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0003

Data Index: 77505 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0003

Data Index: 663937 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0149. Min Act: -0.0003

Data Index: 238768 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1255239 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0134. Min Act: -0.0003

Data Index: 661928 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0003

Data Index: 593857 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1538835 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1128373 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1246751 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0134. Min Act: -0.0003

Data Index: 98299 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0138. Min Act: -0.0003

Data Index: 21452 (C4 (Web Text))

Max Activating Token Index: 279