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

Dataset: The Pile

Neuron 30 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: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0000

Data Index: 472719 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0544. Min Act: -0.0000

Data Index: 39261 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0494. Min Act: -0.0000

Data Index: 476614 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0459. Min Act: 0.0000

Data Index: 234037 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1676506 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0463. Min Act: 0.0000

Data Index: 961925 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0435. Min Act: 0.0000

Data Index: 1260527 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1280792 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0402. Min Act: 0.0000

Data Index: 1970025 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0409. Min Act: -0.0000

Data Index: 261323 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0399. Min Act: -0.0000

Data Index: 594764 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0387. Min Act: 0.0000

Data Index: 667799 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0383. Min Act: 0.0000

Data Index: 1107211 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0377. Min Act: 0.0000

Data Index: 629154 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1477550 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1075903 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0371. Min Act: -0.0000

Data Index: 131949 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0385. Min Act: 0.0000

Data Index: 584076 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0370. Min Act: 0.0000

Data Index: 836549 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0365. Min Act: -0.0000

Data Index: 997740 (The Pile)

Max Activating Token Index: 385