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

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

Neuron 3334 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3890. Min Act: -0.0001

Data Index: 182374 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3262. Min Act: -0.0001

Data Index: 1073439 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3446. Min Act: -0.0001

Data Index: 294869 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2949. Min Act: -0.0001

Data Index: 429353 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2960. Min Act: -0.0001

Data Index: 930254 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2894. Min Act: -0.0001

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2585. Min Act: -0.0001

Data Index: 24204 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3148. Min Act: -0.0001

Data Index: 249672 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2787. Min Act: -0.0001

Data Index: 543414 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1131824 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2516. Min Act: -0.0001

Data Index: 775710 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2455. Min Act: -0.0001

Data Index: 668497 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1287579 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2682. Min Act: -0.0001

Data Index: 451710 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2413. Min Act: -0.0001

Data Index: 577546 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2371. Min Act: -0.0001

Data Index: 527484 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2645. Min Act: -0.0001

Data Index: 754773 (C4 (Web Text))

Max Activating Token Index: 413