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

Dataset: The Pile

Neuron 4434 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: 3.6449. Min Range: -3.6449

Max Act: 3.5733. Min Act: -0.0000

Data Index: 291226 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.6449. Min Act: -0.0000

Data Index: 1043320 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1295709 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.5479. Min Act: -0.0000

Data Index: 317842 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.2062. Min Act: -0.0000

Data Index: 860456 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.2180. Min Act: -0.0000

Data Index: 1170350 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.3053. Min Act: -0.0000

Data Index: 195928 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1225. Min Act: -0.0000

Data Index: 148004 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.2544. Min Act: -0.0000

Data Index: 1350882 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.2533. Min Act: -0.0000

Data Index: 51967 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.4291. Min Act: -0.0000

Data Index: 1400246 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.0317. Min Act: -0.0000

Data Index: 1696827 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.4877. Min Act: -0.0000

Data Index: 40663 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1537. Min Act: -0.0000

Data Index: 1248029 (The Pile)

Max Activating Token Index: 5

Text #14

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1491. Min Act: -0.0000

Data Index: 1391422 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.3754. Min Act: -0.0000

Data Index: 415517 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9963. Min Act: -0.0000

Data Index: 485189 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 3.6449. Min Range: -3.6449

Max Act: 2.9875. Min Act: -0.0000

Data Index: 1185865 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.1020. Min Act: -0.0000

Data Index: 82805 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 3.6449. Min Range: -3.6449

Max Act: 3.0911. Min Act: -0.0000

Data Index: 1616392 (The Pile)

Max Activating Token Index: 405