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

Dataset: The Pile

Neuron 2825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1489547 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1395719 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7971. Min Act: -0.0000

Data Index: 959999 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8319. Min Act: -0.0000

Data Index: 988424 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.8512. Min Act: -0.0000

Data Index: 238305 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7289. Min Act: -0.0000

Data Index: 953538 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1624813 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7845. Min Act: -0.0000

Data Index: 620394 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7727. Min Act: -0.0000

Data Index: 274370 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1672928 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1668269 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1376530 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1203146 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1526786 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6605. Min Act: -0.0000

Data Index: 80406 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6288. Min Act: -0.0000

Data Index: 93634 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1890150 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1675659 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1256844 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.9442. Min Range: -0.9442

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1845126 (The Pile)

Max Activating Token Index: 941