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

Dataset: The Pile

Neuron 483 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4826. Min Range: -3.4826

Max Act: 3.4826. Min Act: -0.0000

Data Index: 1598714 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.4826. Min Range: -3.4826

Max Act: 3.2748. Min Act: -0.0000

Data Index: 1919438 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.2856. Min Act: -0.0000

Data Index: 1144498 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.1027. Min Act: -0.0000

Data Index: 1067024 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1250324 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.0567. Min Act: -0.0000

Data Index: 1381427 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.1680. Min Act: -0.0000

Data Index: 856687 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.9415. Min Act: -0.0000

Data Index: 802928 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 3.4826. Min Range: -3.4826

Max Act: 2.0269. Min Act: -0.0000

Data Index: 1790623 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.7974. Min Act: -0.0000

Data Index: 545937 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.6744. Min Act: -0.0000

Data Index: 1109749 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.6680. Min Act: -0.0000

Data Index: 497327 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.6576. Min Act: -0.0000

Data Index: 772698 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1662389 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1366203 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1434127 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1707247 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1100668 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.5814. Min Act: -0.0000

Data Index: 103409 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 3.4826. Min Range: -3.4826

Max Act: 1.5763. Min Act: -0.0000

Data Index: 790984 (The Pile)

Max Activating Token Index: 73