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

Dataset: The Pile

Neuron 2493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7497. Min Act: -0.0000

Data Index: 312414 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1474810 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6770. Min Act: -0.0000

Data Index: 544245 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1748190 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6869. Min Act: -0.0000

Data Index: 699712 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7033. Min Act: -0.0000

Data Index: 764450 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6494. Min Act: 0.0000

Data Index: 1701201 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6221. Min Act: -0.0000

Data Index: 91478 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6626. Min Act: -0.0000

Data Index: 699727 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1683091 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1337144 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6257. Min Act: -0.0000

Data Index: 193817 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6603. Min Act: 0.0000

Data Index: 842080 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5786. Min Act: -0.0000

Data Index: 2617 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1148316 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1960802 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5479. Min Act: -0.0000

Data Index: 339470 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1882493 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5556. Min Act: -0.0000

Data Index: 361079 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5529. Min Act: 0.0000

Data Index: 744426 (The Pile)

Max Activating Token Index: 532