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

Dataset: The Pile

Neuron 4387 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: 1.0567. Min Range: -1.0567

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1993528 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0118. Min Act: -0.0000

Data Index: 984397 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1820369 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.6250. Min Act: 0.0000

Data Index: 314627 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5619. Min Act: -0.0000

Data Index: 139053 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1899503 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.6274. Min Act: -0.0000

Data Index: 405242 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1647959 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5159. Min Act: -0.0000

Data Index: 377830 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1484490 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5327. Min Act: -0.0000

Data Index: 341814 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1176762 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5074. Min Act: -0.0000

Data Index: 336352 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.5044. Min Act: -0.0000

Data Index: 905771 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1288552 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1492314 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4589. Min Act: -0.0000

Data Index: 727206 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4814. Min Act: -0.0000

Data Index: 841348 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4758. Min Act: -0.0000

Data Index: 649536 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1829527 (The Pile)

Max Activating Token Index: 533