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

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

Neuron 81 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0006

Data Index: 209341 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0167. Min Act: -0.0006

Data Index: 247916 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0168. Min Act: -0.0006

Data Index: 761295 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1334467 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0160. Min Act: -0.0006

Data Index: 628057 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1332221 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0161. Min Act: -0.0006

Data Index: 456778 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1086068 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0153. Min Act: -0.0006

Data Index: 507113 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0149. Min Act: -0.0006

Data Index: 180442 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1304695 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0152. Min Act: -0.0006

Data Index: 189574 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0148. Min Act: -0.0006

Data Index: 860656 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0147. Min Act: -0.0006

Data Index: 353099 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0006

Data Index: 96727 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0006

Data Index: 472197 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0145. Min Act: -0.0006

Data Index: 252094 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0006

Data Index: 577443 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0143. Min Act: -0.0006

Data Index: 205264 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0006

Data Index: 20868 (C4 (Web Text))

Max Activating Token Index: 129