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

Dataset: The Pile

Neuron 999 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: 1.0593. Min Range: -1.0593

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1172499 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1611507 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1605405 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1027522 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1686024 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7235. Min Act: -0.0000

Data Index: 741137 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7216. Min Act: -0.0000

Data Index: 19597 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1191495 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1596496 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1858180 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1106231 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1319946 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1908994 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5965. Min Act: -0.0000

Data Index: 581726 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1756863 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1251978 (The Pile)

Max Activating Token Index: 593

Text #16

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5846. Min Act: -0.0000

Data Index: 979579 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1702007 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1377330 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1023079 (The Pile)

Max Activating Token Index: 29