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

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

Neuron 1008 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.8264. Min Act: -0.0000

Data Index: 224340 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.8249. Min Act: -0.0000

Data Index: 85438 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7902. Min Act: 0.0001

Data Index: 1188992 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7071. Min Act: -0.0000

Data Index: 989471 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1081976 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.7159. Min Act: -0.0000

Data Index: 692823 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6849. Min Act: -0.0000

Data Index: 125473 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6925. Min Act: -0.0000

Data Index: 373559 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6976. Min Act: -0.0000

Data Index: 758526 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6918. Min Act: -0.0000

Data Index: 52439 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6909. Min Act: -0.0000

Data Index: 46414 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6723. Min Act: -0.0000

Data Index: 315277 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6783. Min Act: -0.0000

Data Index: 446538 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6679. Min Act: -0.0000

Data Index: 537482 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6632. Min Act: -0.0000

Data Index: 705986 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6639. Min Act: -0.0000

Data Index: 105586 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6428. Min Act: -0.0000

Data Index: 902274 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1147293 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6355. Min Act: -0.0000

Data Index: 32247 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.8264. Min Range: -0.8264

Max Act: 0.6471. Min Act: -0.0000

Data Index: 260784 (C4 (Web Text))

Max Activating Token Index: 976