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

Dataset: The Pile

Neuron 1002 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6463. Min Act: -0.0000

Data Index: 914471 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1110323 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1060048 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6627. Min Act: -0.0000

Data Index: 803996 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6478. Min Act: -0.0000

Data Index: 838220 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1772476 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1694443 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5632. Min Act: -0.0000

Data Index: 158544 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1241285 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1326139 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1791494 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4506. Min Act: -0.0000

Data Index: 772112 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1993277 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1429925 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1777449 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4442. Min Act: -0.0000

Data Index: 186559 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1809516 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4310. Min Act: -0.0000

Data Index: 953807 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1683511 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4065. Min Act: -0.0000

Data Index: 19118 (The Pile)

Max Activating Token Index: 334