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

Dataset: The Pile

Neuron 3776 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1976. Min Range: -1.1976

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1019542 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.1976. Min Range: -1.1976

Max Act: 1.0494. Min Act: -0.0000

Data Index: 19819 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1819500 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1921567 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8135. Min Act: -0.0000

Data Index: 165691 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1500382 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9255. Min Act: -0.0000

Data Index: 237817 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8716. Min Act: -0.0000

Data Index: 534667 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8180. Min Act: -0.0000

Data Index: 791983 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9278. Min Act: -0.0000

Data Index: 84654 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8458. Min Act: -0.0000

Data Index: 27478 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8026. Min Act: -0.0000

Data Index: 259892 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1783180 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1824640 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8280. Min Act: 0.0001

Data Index: 418475 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8349. Min Act: -0.0000

Data Index: 50659 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.8826. Min Act: -0.0000

Data Index: 855480 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.7692. Min Act: -0.0000

Data Index: 563140 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.9218. Min Act: -0.0000

Data Index: 540575 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 1.1976. Min Range: -1.1976

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1305500 (The Pile)

Max Activating Token Index: 213