Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3793 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1347990 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1785007 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0363. Min Act: -0.0000

Data Index: 302642 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1620285 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0345. Min Act: -0.0000

Data Index: 738419 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0355. Min Act: -0.0000

Data Index: 713467 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0352. Min Act: -0.0000

Data Index: 975757 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1197018 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0348. Min Act: -0.0000

Data Index: 776546 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1914922 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0346. Min Act: -0.0000

Data Index: 930544 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0342. Min Act: -0.0000

Data Index: 362177 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0339. Min Act: -0.0000

Data Index: 771963 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0338. Min Act: -0.0000

Data Index: 548141 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0337. Min Act: -0.0000

Data Index: 496692 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1577534 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0337. Min Act: 0.0000

Data Index: 875277 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0336. Min Act: -0.0000

Data Index: 705660 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0337. Min Act: -0.0000

Data Index: 727532 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1525226 (The Pile)

Max Activating Token Index: 742