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

Dataset: The Pile

Neuron 530 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: 1.7966. Min Range: -1.7966

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1492769 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.7304. Min Act: -0.0000

Data Index: 665855 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1284832 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.4582. Min Act: -0.0000

Data Index: 268603 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1617456 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.4636. Min Act: -0.0000

Data Index: 1028331 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.6051. Min Act: -0.0000

Data Index: 646408 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.3364. Min Act: -0.0000

Data Index: 463840 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1141215 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2819. Min Act: -0.0000

Data Index: 325646 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1446190 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2511. Min Act: -0.0000

Data Index: 219213 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1693532 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1109. Min Act: -0.0000

Data Index: 10534 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1914. Min Act: -0.0000

Data Index: 618973 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2294. Min Act: -0.0000

Data Index: 489960 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1431. Min Act: -0.0000

Data Index: 593576 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2191. Min Act: -0.0000

Data Index: 443183 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1462. Min Act: -0.0000

Data Index: 306357 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1988. Min Act: -0.0000

Data Index: 401660 (The Pile)

Max Activating Token Index: 5