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

Dataset: The Pile

Neuron 551 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: 1.0138. Min Range: -1.0138

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1069833 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.7863. Min Act: -0.0000

Data Index: 786941 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.7055. Min Act: -0.0000

Data Index: 608241 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1110373 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6878. Min Act: -0.0000

Data Index: 251446 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.7424. Min Act: -0.0000

Data Index: 614231 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6881. Min Act: -0.0000

Data Index: 721844 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1247998 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1184311 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.7341. Min Act: -0.0000

Data Index: 780615 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6566. Min Act: -0.0000

Data Index: 932180 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1447135 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1228298 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6461. Min Act: -0.0000

Data Index: 212653 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1929095 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6434. Min Act: -0.0000

Data Index: 311538 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1122756 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.5531. Min Act: -0.0000

Data Index: 801221 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1372537 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 1.0138. Min Range: -1.0138

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1453452 (The Pile)

Max Activating Token Index: 671