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

Dataset: The Pile

Neuron 4352 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: 1.6665. Min Range: -1.6665

Max Act: 1.6470. Min Act: -0.0000

Data Index: 892032 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1454020 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.6665. Min Act: -0.0000

Data Index: 551609 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1133421 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.3153. Min Act: -0.0000

Data Index: 11255 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1195584 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1889833 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1079931 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2704. Min Act: -0.0000

Data Index: 10020 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2784. Min Act: -0.0000

Data Index: 445007 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2805. Min Act: -0.0000

Data Index: 979014 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1801335 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1506688 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1519653 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2174. Min Act: -0.0000

Data Index: 237481 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1054294 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1400188 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1794008 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1930. Min Act: -0.0000

Data Index: 551807 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1344343 (The Pile)

Max Activating Token Index: 533