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

Dataset: The Pile

Neuron 2914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3212. Min Act: 0.0000

Data Index: 400523 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1447563 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3298. Min Act: -0.0000

Data Index: 90274 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1189436 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1880277 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1473286 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1215829 (The Pile)

Max Activating Token Index: 846

Text #7

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1534579 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1581703 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1077226 (The Pile)

Max Activating Token Index: 95

Text #10

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1860332 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2830. Min Act: -0.0000

Data Index: 138805 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2757. Min Act: -0.0000

Data Index: 488886 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2867. Min Act: -0.0000

Data Index: 141393 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2738. Min Act: -0.0000

Data Index: 129544 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2643. Min Act: -0.0000

Data Index: 737052 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2593. Min Act: -0.0000

Data Index: 515030 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2618. Min Act: 0.0000

Data Index: 799173 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1825029 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1698230 (The Pile)

Max Activating Token Index: 87