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

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

Neuron 70 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: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0003

Data Index: 209368 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1307350 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0164. Min Act: -0.0003

Data Index: 276944 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0171. Min Act: -0.0003

Data Index: 882485 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0169. Min Act: -0.0003

Data Index: 66095 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0170. Min Act: -0.0003

Data Index: 479673 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1391415 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1074044 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1486103 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1308374 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0159. Min Act: -0.0003

Data Index: 73428 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0158. Min Act: -0.0003

Data Index: 281984 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1144362 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1592955 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0155. Min Act: -0.0003

Data Index: 175498 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1411032 (Python Code)

Max Activating Token Index: 283

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0156. Min Act: -0.0003

Data Index: 871491 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1429528 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0154. Min Act: -0.0003

Data Index: 280375 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1210158 (C4 (Web Text))

Max Activating Token Index: 493