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

Dataset: The Pile

Neuron 4372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3788. Min Act: -0.0000

Data Index: 950541 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3445. Min Act: -0.0000

Data Index: 588062 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1043292 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3681. Min Act: -0.0000

Data Index: 391808 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3678. Min Act: -0.0000

Data Index: 255448 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1308430 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1032639 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3623. Min Act: -0.0000

Data Index: 915904 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1424253 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3370. Min Act: -0.0000

Data Index: 839767 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1974708 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3383. Min Act: -0.0000

Data Index: 937799 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1111668 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3817. Min Act: -0.0000

Data Index: 552827 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1061039 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3303. Min Act: -0.0000

Data Index: 665396 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1477403 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3669. Min Act: -0.0000

Data Index: 316403 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3502. Min Act: -0.0000

Data Index: 270650 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3205. Min Act: -0.0000

Data Index: 539525 (The Pile)

Max Activating Token Index: 433