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

Dataset: The Pile

Neuron 448 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: 0.9322. Min Range: -0.9322

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1189190 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.9322. Min Act: -0.0000

Data Index: 936273 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.8664. Min Act: -0.0000

Data Index: 42217 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.8322. Min Act: -0.0000

Data Index: 671780 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7813. Min Act: -0.0000

Data Index: 580512 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.8123. Min Act: -0.0000

Data Index: 214257 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7814. Min Act: -0.0000

Data Index: 285431 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1304477 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1098675 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1000843 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7901. Min Act: -0.0000

Data Index: 439152 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1980562 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7536. Min Act: -0.0000

Data Index: 775357 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6988. Min Act: -0.0000

Data Index: 452261 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1489529 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.7157. Min Act: -0.0000

Data Index: 587199 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6937. Min Act: -0.0000

Data Index: 431234 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6947. Min Act: -0.0000

Data Index: 867455 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1618248 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 0.9322. Min Range: -0.9322

Max Act: 0.6772. Min Act: -0.0000

Data Index: 713966 (The Pile)

Max Activating Token Index: 509