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

Dataset: The Pile

Neuron 1415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8433. Min Act: -0.0000

Data Index: 421488 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1548675 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1116696 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5906. Min Act: -0.0000

Data Index: 866591 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5676. Min Act: 0.0000

Data Index: 498443 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5357. Min Act: 0.0000

Data Index: 1943501 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1979709 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5198. Min Act: 0.0000

Data Index: 1525903 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5186. Min Act: 0.0000

Data Index: 532510 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1905758 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1492674 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1625702 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4659. Min Act: -0.0000

Data Index: 801733 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1421046 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4468. Min Act: 0.0000

Data Index: 1260419 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4452. Min Act: 0.0000

Data Index: 1045327 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4223. Min Act: 0.0000

Data Index: 193015 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1275921 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4438. Min Act: -0.0000

Data Index: 437850 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4247. Min Act: -0.0000

Data Index: 329126 (The Pile)

Max Activating Token Index: 554