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

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

Neuron 4640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1239055 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1083821 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3815. Min Act: -0.0000

Data Index: 265806 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1315576 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3080. Min Act: -0.0000

Data Index: 493986 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3158. Min Act: -0.0000

Data Index: 461118 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3103. Min Act: -0.0000

Data Index: 786039 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1008886 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2795. Min Act: -0.0000

Data Index: 151287 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1085703 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2619. Min Act: -0.0000

Data Index: 484152 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2577. Min Act: -0.0000

Data Index: 799055 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2605. Min Act: -0.0000

Data Index: 187810 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2723. Min Act: -0.0000

Data Index: 99678 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1075258 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2522. Min Act: -0.0000

Data Index: 84372 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1205757 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2321. Min Act: -0.0000

Data Index: 259575 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1345929 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1250026 (C4 (Web Text))

Max Activating Token Index: 729