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

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

Neuron 4836 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1276152 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4662. Min Act: -0.0000

Data Index: 333286 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4948. Min Act: -0.0000

Data Index: 769309 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4568. Min Act: -0.0000

Data Index: 721619 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4813. Min Act: -0.0000

Data Index: 367462 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4359. Min Act: -0.0000

Data Index: 752449 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4576. Min Act: -0.0000

Data Index: 7355 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1240851 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4375. Min Act: -0.0000

Data Index: 779467 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4062. Min Act: -0.0000

Data Index: 323650 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4076. Min Act: -0.0000

Data Index: 13897 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1253402 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4043. Min Act: -0.0000

Data Index: 484300 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4336. Min Act: -0.0000

Data Index: 426465 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4065. Min Act: -0.0000

Data Index: 767616 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3854. Min Act: -0.0000

Data Index: 634524 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3783. Min Act: -0.0000

Data Index: 551766 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3917. Min Act: -0.0000

Data Index: 416023 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1296280 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1297371 (C4 (Web Text))

Max Activating Token Index: 262