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

Dataset: The Pile

Neuron 2761 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1494207 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1619584 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1244992 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1633873 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1861259 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7858. Min Act: -0.0000

Data Index: 737275 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7802. Min Act: -0.0000

Data Index: 410648 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7717. Min Act: -0.0000

Data Index: 828883 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7744. Min Act: -0.0000

Data Index: 654027 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1053727 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7178. Min Act: -0.0000

Data Index: 327764 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1500179 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1124814 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7889. Min Act: -0.0000

Data Index: 460278 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1477297 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1462272 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7612. Min Act: -0.0000

Data Index: 822800 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7306. Min Act: -0.0000

Data Index: 659876 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1733773 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7399. Min Act: -0.0000

Data Index: 154835 (The Pile)

Max Activating Token Index: 590