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

Dataset: The Pile

Neuron 530 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: 0.4508. Min Range: -0.4508

Max Act: 0.4508. Min Act: -0.0000

Data Index: 719262 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1984143 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3772. Min Act: -0.0000

Data Index: 591416 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3346. Min Act: -0.0000

Data Index: 684213 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1665360 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1804833 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1155455 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1445193 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1295999 (The Pile)

Max Activating Token Index: 865

Text #9

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1589549 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1536388 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1239950 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1796610 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1223910 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1857037 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3303. Min Act: -0.0000

Data Index: 646646 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1926647 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3107. Min Act: -0.0000

Data Index: 555684 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1884666 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3167. Min Act: -0.0000

Data Index: 460079 (The Pile)

Max Activating Token Index: 903