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

Dataset: The Pile

Neuron 3535 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: 0.8728. Min Range: -0.8728

Max Act: 0.8728. Min Act: -0.0000

Data Index: 894278 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1979825 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1222686 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1749266 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6807. Min Act: -0.0000

Data Index: 973792 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1503715 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7162. Min Act: -0.0000

Data Index: 713205 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1737505 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6871. Min Act: -0.0000

Data Index: 735577 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1567968 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1805041 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1896824 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1247404 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1229737 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6285. Min Act: -0.0000

Data Index: 862458 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1162517 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1953429 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1578957 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6231. Min Act: -0.0000

Data Index: 73564 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6388. Min Act: -0.0000

Data Index: 370976 (The Pile)

Max Activating Token Index: 561