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

Dataset: The Pile

Neuron 1739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1808779 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1826633 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7368. Min Act: -0.0000

Data Index: 966898 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6326. Min Act: -0.0000

Data Index: 708422 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6544. Min Act: -0.0000

Data Index: 635129 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1912703 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6543. Min Act: -0.0000

Data Index: 697096 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7430. Min Act: -0.0000

Data Index: 781237 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1373980 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5970. Min Act: -0.0000

Data Index: 844564 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6283. Min Act: -0.0000

Data Index: 833942 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6502. Min Act: -0.0000

Data Index: 727821 (The Pile)

Max Activating Token Index: 482

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5633. Min Act: 0.0000

Data Index: 22188 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5728. Min Act: -0.0000

Data Index: 110853 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1548217 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5515. Min Act: -0.0000

Data Index: 535428 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5863. Min Act: -0.0000

Data Index: 801174 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1059624 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1817425 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5586. Min Act: -0.0000

Data Index: 441486 (The Pile)

Max Activating Token Index: 58