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

Dataset: The Pile

Neuron 2470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1756. Min Range: -4.1756

Max Act: 4.1756. Min Act: -0.0000

Data Index: 927093 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.4219. Min Act: -0.0000

Data Index: 1878297 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.3967. Min Act: -0.0000

Data Index: 1974845 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.1208. Min Act: -0.0000

Data Index: 1558401 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.2045. Min Act: -0.0000

Data Index: 1151746 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.0510. Min Act: -0.0000

Data Index: 839369 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.8741. Min Act: -0.0000

Data Index: 736077 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.8293. Min Act: -0.0000

Data Index: 570336 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.8217. Min Act: 0.0001

Data Index: 66792 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.7535. Min Act: -0.0000

Data Index: 1769058 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.7830. Min Act: -0.0000

Data Index: 844211 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.7017. Min Act: -0.0000

Data Index: 1227920 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1585312 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.5540. Min Act: -0.0000

Data Index: 326637 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.8058. Min Act: -0.0000

Data Index: 1075383 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.5130. Min Act: -0.0000

Data Index: 662925 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.7841. Min Act: -0.0000

Data Index: 1250272 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 4.1756. Min Range: -4.1756

Max Act: 3.0277. Min Act: 0.0000

Data Index: 830731 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.6554. Min Act: -0.0000

Data Index: 1910093 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 4.1756. Min Range: -4.1756

Max Act: 2.5959. Min Act: -0.0000

Data Index: 1764454 (The Pile)

Max Activating Token Index: 633