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

Dataset: The Pile

Neuron 1338 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: 1.7901. Min Range: -1.7901

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1370577 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.7496. Min Act: -0.0000

Data Index: 600458 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5455. Min Act: -0.0000

Data Index: 167276 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1648450 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.7901. Min Act: -0.0000

Data Index: 128248 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.6731. Min Act: -0.0000

Data Index: 1810917 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1892221 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4491. Min Act: -0.0000

Data Index: 811020 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5539. Min Act: -0.0000

Data Index: 172853 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4605. Min Act: -0.0000

Data Index: 895414 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4621. Min Act: -0.0000

Data Index: 111482 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1305281 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1949846 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1487437 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5143. Min Act: -0.0000

Data Index: 124748 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4249. Min Act: -0.0000

Data Index: 953241 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4504. Min Act: -0.0000

Data Index: 225597 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4277. Min Act: -0.0000

Data Index: 53225 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1292124 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4040. Min Act: -0.0000

Data Index: 742485 (The Pile)

Max Activating Token Index: 865