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

Dataset: The Pile

Neuron 3787 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: 0.9587. Min Range: -0.9587

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1427244 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7975. Min Act: -0.0000

Data Index: 209830 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1398960 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8494. Min Act: -0.0000

Data Index: 51985 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1718999 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1977418 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6824. Min Act: -0.0000

Data Index: 932515 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6867. Min Act: -0.0000

Data Index: 779897 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1983354 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1459917 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1674960 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6356. Min Act: -0.0000

Data Index: 540278 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1431105 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1597012 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1584074 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1009346 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.5841. Min Act: -0.0000

Data Index: 147810 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.5262. Min Act: -0.0000

Data Index: 379508 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1449295 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.5901. Min Act: -0.0000

Data Index: 392526 (The Pile)

Max Activating Token Index: 414