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

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

Neuron 18 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5076. Min Act: -0.0000

Data Index: 773706 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4700. Min Act: -0.0000

Data Index: 737327 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4284. Min Act: 0.0001

Data Index: 1257645 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1177895 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1134648 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3851. Min Act: 0.0000

Data Index: 281026 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3764. Min Act: -0.0000

Data Index: 266859 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3754. Min Act: -0.0000

Data Index: 913790 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3334. Min Act: -0.0000

Data Index: 582035 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3393. Min Act: -0.0000

Data Index: 734012 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1149686 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3379. Min Act: -0.0000

Data Index: 382462 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3423. Min Act: -0.0000

Data Index: 887425 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3518. Min Act: -0.0000

Data Index: 992732 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3466. Min Act: -0.0000

Data Index: 24935 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3360. Min Act: -0.0000

Data Index: 610203 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1273312 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1218219 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1252986 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3299. Min Act: -0.0000

Data Index: 22341 (C4 (Web Text))

Max Activating Token Index: 780