Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1448386 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1738063 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1301840 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1424362 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1178973 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1722436 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6310. Min Act: -0.0000

Data Index: 265320 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1365197 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5959. Min Act: -0.0000

Data Index: 446076 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5709. Min Act: -0.0000

Data Index: 340510 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5620. Min Act: -0.0000

Data Index: 568075 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1496675 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1591143 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1008725 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5514. Min Act: -0.0000

Data Index: 126978 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5668. Min Act: -0.0000

Data Index: 285588 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5579. Min Act: 0.0000

Data Index: 157448 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5265. Min Act: -0.0000

Data Index: 49165 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5901. Min Act: -0.0000

Data Index: 503368 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1583630 (The Pile)

Max Activating Token Index: 304