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

Dataset: The Pile

Neuron 4418 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1421295 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1840936 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3446. Min Act: -0.0000

Data Index: 179697 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1142569 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3411. Min Act: -0.0000

Data Index: 983447 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3324. Min Act: -0.0000

Data Index: 174236 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3671. Min Act: -0.0000

Data Index: 668571 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1593039 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1146680 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2836. Min Act: -0.0000

Data Index: 755875 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2681. Min Act: -0.0000

Data Index: 276883 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2569. Min Act: -0.0000

Data Index: 635763 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1690967 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1344572 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1814511 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1423456 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1682378 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2459. Min Act: -0.0000

Data Index: 342319 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2698. Min Act: -0.0000

Data Index: 124694 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1943902 (The Pile)

Max Activating Token Index: 68