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

Dataset: The Pile

Neuron 1266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1662965 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3785. Min Act: -0.0000

Data Index: 467513 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1768378 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1752930 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2878. Min Act: -0.0000

Data Index: 13090 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1328772 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1168484 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2593. Min Act: -0.0000

Data Index: 709088 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2401. Min Act: -0.0000

Data Index: 899211 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1192873 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2504. Min Act: -0.0000

Data Index: 699955 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2537. Min Act: -0.0000

Data Index: 384460 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1538418 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2173. Min Act: -0.0000

Data Index: 454823 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2689. Min Act: -0.0000

Data Index: 382137 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1829382 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2369. Min Act: -0.0000

Data Index: 635811 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1701762 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2324. Min Act: -0.0000

Data Index: 745037 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1457223 (The Pile)

Max Activating Token Index: 450