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

Dataset: The Pile

Neuron 3594 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: 0.5368. Min Range: -0.5368

Max Act: 0.5306. Min Act: -0.0000

Data Index: 918722 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5368. Min Act: -0.0000

Data Index: 860085 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1982004 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1021500 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1293495 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1567234 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1173756 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1884576 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4703. Min Act: -0.0000

Data Index: 185657 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1300586 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1910045 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1121475 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1529864 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4659. Min Act: -0.0000

Data Index: 701753 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4470. Min Act: -0.0000

Data Index: 782565 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1168498 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4205. Min Act: 0.0000

Data Index: 148379 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4094. Min Act: -0.0000

Data Index: 117848 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4616. Min Act: -0.0000

Data Index: 444270 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4161. Min Act: -0.0000

Data Index: 477231 (The Pile)

Max Activating Token Index: 847