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

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

Neuron 2470 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: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0003

Data Index: 12407 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0170. Min Act: -0.0004

Data Index: 41207 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0167. Min Act: -0.0004

Data Index: 538341 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0164. Min Act: -0.0004

Data Index: 63420 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0161. Min Act: -0.0003

Data Index: 195558 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0164. Min Act: -0.0003

Data Index: 719740 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0161. Min Act: -0.0004

Data Index: 38189 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0003

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0157. Min Act: -0.0004

Data Index: 365797 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0156. Min Act: -0.0004

Data Index: 141092 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0004

Data Index: 507769 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0003

Data Index: 130857 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1198505 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0157. Min Act: -0.0004

Data Index: 807996 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0152. Min Act: -0.0003

Data Index: 417038 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0151. Min Act: -0.0003

Data Index: 838196 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0151. Min Act: -0.0004

Data Index: 104267 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0148. Min Act: -0.0004

Data Index: 211021 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1219216 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0147. Min Act: -0.0003

Data Index: 276167 (C4 (Web Text))

Max Activating Token Index: 45