Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1286456 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2439. Min Act: -0.0000

Data Index: 302897 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1269779 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2502. Min Act: -0.0000

Data Index: 675538 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2769. Min Act: -0.0000

Data Index: 488043 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1364071 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1852705 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2560. Min Act: -0.0000

Data Index: 975158 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2342. Min Act: -0.0000

Data Index: 907552 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1698541 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1162404 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1919088 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2261. Min Act: -0.0000

Data Index: 425759 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2415. Min Act: -0.0000

Data Index: 718716 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1166402 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1993580 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1201452 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2263. Min Act: -0.0000

Data Index: 777130 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1175870 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1385370 (The Pile)

Max Activating Token Index: 964