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

Dataset: The Pile

Neuron 3928 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: 0.8985. Min Range: -0.8985

Max Act: 0.8985. Min Act: -0.0000

Data Index: 104844 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.8282. Min Act: -0.0000

Data Index: 581971 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7721. Min Act: -0.0000

Data Index: 873427 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7869. Min Act: -0.0000

Data Index: 788801 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1638582 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1412239 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1329858 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1497699 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6763. Min Act: -0.0000

Data Index: 108895 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1092504 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1556413 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6352. Min Act: -0.0000

Data Index: 656174 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.6531. Min Act: -0.0000

Data Index: 964566 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1442638 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5690. Min Act: -0.0000

Data Index: 285535 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1476855 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5966. Min Act: -0.0000

Data Index: 980708 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5594. Min Act: -0.0000

Data Index: 357535 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1523022 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.8985. Min Range: -0.8985

Max Act: 0.4993. Min Act: -0.0000

Data Index: 166808 (The Pile)

Max Activating Token Index: 1009