Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3443 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1253014 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1366. Min Act: -0.0002

Data Index: 762205 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1060675 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1384. Min Act: -0.0002

Data Index: 929363 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1095. Min Act: -0.0002

Data Index: 924301 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1045027 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1154. Min Act: -0.0002

Data Index: 52558 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1160. Min Act: -0.0002

Data Index: 153383 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1203. Min Act: -0.0002

Data Index: 257592 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1050. Min Act: -0.0002

Data Index: 957683 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1096. Min Act: -0.0002

Data Index: 3927 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1220. Min Act: -0.0002

Data Index: 578022 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1045492 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1147. Min Act: -0.0002

Data Index: 118415 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1310. Min Act: -0.0002

Data Index: 698498 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1223. Min Act: -0.0002

Data Index: 342934 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1049. Min Act: -0.0002

Data Index: 737730 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0989. Min Act: -0.0002

Data Index: 830247 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1096902 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1074. Min Act: -0.0002

Data Index: 739118 (C4 (Web Text))

Max Activating Token Index: 76