Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 909 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1010751 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1222. Min Act: -0.0002

Data Index: 98580 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1200. Min Act: -0.0002

Data Index: 802402 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1203. Min Act: -0.0002

Data Index: 29217 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1063217 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1229993 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1128. Min Act: -0.0002

Data Index: 485119 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1104. Min Act: -0.0002

Data Index: 507433 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1174. Min Act: -0.0002

Data Index: 134319 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1105. Min Act: -0.0002

Data Index: 883421 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1071. Min Act: -0.0002

Data Index: 707443 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1014. Min Act: -0.0002

Data Index: 277676 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1044. Min Act: -0.0002

Data Index: 676823 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1017. Min Act: -0.0002

Data Index: 28770 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0997. Min Act: -0.0002

Data Index: 873730 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1062037 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1017. Min Act: -0.0002

Data Index: 170984 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1187838 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0980. Min Act: -0.0002

Data Index: 518702 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0972. Min Act: -0.0002

Data Index: 932138 (C4 (Web Text))

Max Activating Token Index: 600