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

Dataset: The Pile

Neuron 4673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.8971. Min Act: -0.0000

Data Index: 786665 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1991016 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.8632. Min Act: -0.0000

Data Index: 935135 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.7565. Min Act: -0.0000

Data Index: 281496 (The Pile)

Max Activating Token Index: 437

Text #4

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.7747. Min Act: -0.0000

Data Index: 402374 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6756. Min Act: -0.0000

Data Index: 759052 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6917. Min Act: -0.0000

Data Index: 133737 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1759580 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6344. Min Act: -0.0000

Data Index: 995555 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1889194 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6548. Min Act: -0.0000

Data Index: 39429 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6001. Min Act: -0.0000

Data Index: 42983 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1962417 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1418540 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6177. Min Act: -0.0000

Data Index: 478405 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6097. Min Act: -0.0000

Data Index: 657593 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1623917 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.5995. Min Act: -0.0000

Data Index: 965738 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6201. Min Act: -0.0000

Data Index: 382241 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.8971. Min Range: -0.8971

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1954110 (The Pile)

Max Activating Token Index: 645