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

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

Neuron 2075 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: 2.4207. Min Range: -2.4207

Max Act: 2.4207. Min Act: -0.0000

Data Index: 317725 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 2.4207. Min Range: -2.4207

Max Act: 2.1598. Min Act: -0.0000

Data Index: 198889 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.8584. Min Act: -0.0000

Data Index: 584760 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.9325. Min Act: -0.0000

Data Index: 655829 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.9072. Min Act: -0.0000

Data Index: 189840 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.4207. Min Range: -2.4207

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1337603 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6511. Min Act: -0.0000

Data Index: 103610 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.8447. Min Act: -0.0000

Data Index: 1169654 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.7622. Min Act: -0.0000

Data Index: 142418 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.7335. Min Act: -0.0000

Data Index: 355356 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6352. Min Act: -0.0000

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6305. Min Act: -0.0000

Data Index: 484435 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1144718 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6118. Min Act: -0.0000

Data Index: 429798 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6794. Min Act: -0.0000

Data Index: 426441 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.5757. Min Act: -0.0000

Data Index: 684199 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6654. Min Act: -0.0000

Data Index: 322833 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.6572. Min Act: -0.0000

Data Index: 715107 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.7539. Min Act: -0.0000

Data Index: 155748 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 2.4207. Min Range: -2.4207

Max Act: 1.5446. Min Act: -0.0000

Data Index: 327046 (C4 (Web Text))

Max Activating Token Index: 1022