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

Dataset: The Pile

Neuron 3683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1610230 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0521. Min Act: -0.0000

Data Index: 9969 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1724673 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0110. Min Act: -0.0000

Data Index: 136061 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0324. Min Act: -0.0000

Data Index: 737613 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9443. Min Act: -0.0000

Data Index: 149897 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9138. Min Act: -0.0000

Data Index: 417580 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9895. Min Act: -0.0000

Data Index: 442816 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9479. Min Act: -0.0000

Data Index: 207425 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1167314 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8627. Min Act: -0.0000

Data Index: 151186 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1716629 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8487. Min Act: -0.0000

Data Index: 152528 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.7181. Min Act: -0.0000

Data Index: 439002 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8506. Min Act: -0.0000

Data Index: 353756 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.7637. Min Act: -0.0000

Data Index: 862902 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8726. Min Act: -0.0000

Data Index: 396626 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1437275 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8185. Min Act: -0.0000

Data Index: 116121 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1770798 (The Pile)

Max Activating Token Index: 801