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

Dataset: The Pile

Neuron 3626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.5511. Min Act: -0.0000

Data Index: 672013 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.3946. Min Act: -0.0000

Data Index: 398479 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.1409. Min Act: -0.0000

Data Index: 456282 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.8881. Min Act: -0.0000

Data Index: 1432358 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.6237. Min Act: -0.0000

Data Index: 1267164 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.9756. Min Act: -0.0000

Data Index: 1658381 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.9699. Min Act: -0.0000

Data Index: 46162 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.6808. Min Act: -0.0000

Data Index: 867637 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.0541. Min Act: -0.0000

Data Index: 1320006 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.6590. Min Act: -0.0000

Data Index: 1274510 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.0006. Min Act: -0.0000

Data Index: 811813 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.1739. Min Act: -0.0000

Data Index: 684646 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.9360. Min Act: -0.0000

Data Index: 1547791 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.1258. Min Act: -0.0000

Data Index: 599316 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 5.6808. Min Range: -5.6808

Max Act: 5.2825. Min Act: -0.0000

Data Index: 496339 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.8556. Min Act: -0.0000

Data Index: 1881811 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.7715. Min Act: -0.0000

Data Index: 295258 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.8331. Min Act: -0.0000

Data Index: 1706637 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.6132. Min Act: -0.0000

Data Index: 1664647 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 5.6808. Min Range: -5.6808

Max Act: 4.4560. Min Act: -0.0000

Data Index: 1249240 (The Pile)

Max Activating Token Index: 550