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

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

Neuron 3859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.9403. Min Act: -0.0000

Data Index: 259104 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.8949. Min Act: -0.0000

Data Index: 451225 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.8526. Min Act: -0.0000

Data Index: 315399 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.8269. Min Act: -0.0000

Data Index: 913777 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1080135 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1001050 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.6660. Min Act: -0.0000

Data Index: 1263063 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1069778 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5085. Min Act: -0.0000

Data Index: 393058 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.6581. Min Act: -0.0000

Data Index: 271316 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5403. Min Act: -0.0000

Data Index: 253967 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1194497 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5039. Min Act: -0.0000

Data Index: 48727 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4941. Min Act: -0.0000

Data Index: 291684 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4604. Min Act: -0.0000

Data Index: 474566 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.3685. Min Act: -0.0000

Data Index: 83231 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4401. Min Act: -0.0000

Data Index: 215412 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1642573 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4192. Min Act: -0.0000

Data Index: 131100 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.2941. Min Act: -0.0000

Data Index: 333055 (C4 (Web Text))

Max Activating Token Index: 778