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

Dataset: The Pile

Neuron 4784 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7748. Min Act: -0.0000

Data Index: 303986 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 300357 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1279686 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7450. Min Act: -0.0000

Data Index: 73538 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1567677 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1455407 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1119020 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1366936 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1768045 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1985503 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7006. Min Act: -0.0000

Data Index: 644837 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1239365 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6959. Min Act: -0.0000

Data Index: 773851 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1670277 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1897497 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1115142 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1953354 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1285433 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6741. Min Act: -0.0000

Data Index: 457494 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1224549 (The Pile)

Max Activating Token Index: 78