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

Dataset: The Pile

Neuron 3379 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.5243. Min Act: -0.0000

Data Index: 995522 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1346819 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.5297. Min Act: -0.0000

Data Index: 446505 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1857911 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0181. Min Act: -0.0001

Data Index: 511533 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1308427 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.3025. Min Act: 0.0000

Data Index: 1017974 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1302070 (The Pile)

Max Activating Token Index: 846

Text #8

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2205. Min Act: -0.0000

Data Index: 806088 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1257940 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0631. Min Act: -0.0000

Data Index: 70971 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0760. Min Act: -0.0001

Data Index: 1110120 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.5297. Min Range: -1.5297

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1266916 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9679. Min Act: -0.0001

Data Index: 593662 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1210346 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9468. Min Act: 0.0000

Data Index: 1165015 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9319. Min Act: -0.0000

Data Index: 262635 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.8675. Min Act: -0.0001

Data Index: 611380 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9550. Min Act: -0.0001

Data Index: 621593 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 1.5297. Min Range: -1.5297

Max Act: 0.9101. Min Act: -0.0001

Data Index: 110932 (The Pile)

Max Activating Token Index: 1002