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

Dataset: The Pile

Neuron 1638 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1904051 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1439686 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1750667 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5627. Min Act: -0.0000

Data Index: 763321 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6036. Min Act: -0.0000

Data Index: 377042 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5542. Min Act: -0.0000

Data Index: 802383 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1971372 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6279. Min Act: -0.0000

Data Index: 201947 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5373. Min Act: -0.0000

Data Index: 649667 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5245. Min Act: -0.0000

Data Index: 947347 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1257219 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5966. Min Act: -0.0000

Data Index: 792802 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5320. Min Act: -0.0000

Data Index: 918962 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.4926. Min Act: -0.0000

Data Index: 627889 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1663783 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5103. Min Act: -0.0000

Data Index: 876173 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5501. Min Act: -0.0000

Data Index: 394449 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5672. Min Act: -0.0000

Data Index: 463551 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1047350 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.5318. Min Act: -0.0000

Data Index: 415103 (The Pile)

Max Activating Token Index: 281