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

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

Neuron 4113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.7331. Min Act: -0.0000

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1302529 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.5207. Min Act: -0.0000

Data Index: 783939 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1223563 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.4533. Min Act: -0.0000

Data Index: 158751 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.4728. Min Act: -0.0000

Data Index: 396672 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.4569. Min Act: -0.0000

Data Index: 368367 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1345934 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.3530. Min Act: -0.0000

Data Index: 873357 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.3310. Min Act: -0.0000

Data Index: 624136 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.3308. Min Act: -0.0000

Data Index: 448003 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.3535. Min Act: -0.0000

Data Index: 205315 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2960. Min Act: -0.0000

Data Index: 876641 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2682. Min Act: -0.0000

Data Index: 34688 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2703. Min Act: -0.0000

Data Index: 640902 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2777. Min Act: -0.0000

Data Index: 595531 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2484. Min Act: -0.0000

Data Index: 922508 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1027614 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2523. Min Act: -0.0000

Data Index: 695073 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.7331. Min Range: -0.7331

Max Act: 0.2339. Min Act: -0.0000

Data Index: 48987 (C4 (Web Text))

Max Activating Token Index: 826