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

Dataset: The Pile

Neuron 1284 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5769. Min Range: -1.5769

Max Act: 1.5769. Min Act: -0.0000

Data Index: 102165 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1781525 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3667. Min Act: -0.0000

Data Index: 585528 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3275. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3296. Min Act: -0.0000

Data Index: 163621 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3616. Min Act: -0.0000

Data Index: 12545 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3281. Min Act: -0.0000

Data Index: 619343 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1982740 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1668861 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1139079 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.2802. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3440. Min Act: -0.0000

Data Index: 381757 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3169. Min Act: -0.0000

Data Index: 899640 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3184. Min Act: -0.0000

Data Index: 605461 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3216. Min Act: -0.0000

Data Index: 785959 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1531861 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1334363 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.5769. Min Range: -1.5769

Max Act: 0.3019. Min Act: -0.0000

Data Index: 451991 (The Pile)

Max Activating Token Index: 480