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

Dataset: The Pile

Neuron 4699 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1989523 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0366. Min Act: -0.0000

Data Index: 332941 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0364. Min Act: -0.0000

Data Index: 259455 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0362. Min Act: -0.0000

Data Index: 511565 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0361. Min Act: -0.0000

Data Index: 1653730 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0362. Min Act: -0.0000

Data Index: 708173 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0361. Min Act: -0.0000

Data Index: 961519 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0360. Min Act: -0.0000

Data Index: 353605 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0359. Min Act: -0.0000

Data Index: 862973 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1789826 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: 0.0000

Data Index: 1739683 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: 0.0000

Data Index: 65305 (The Pile)

Max Activating Token Index: 4

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: 0.0000

Data Index: 1091038 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: -0.0000

Data Index: 892480 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1867772 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: 0.0000

Data Index: 438720 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0357. Min Act: -0.0000

Data Index: 249643 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1393275 (The Pile)

Max Activating Token Index: 2

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0353. Min Act: 0.0000

Data Index: 1625635 (The Pile)

Max Activating Token Index: 2

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1480556 (The Pile)

Max Activating Token Index: 2