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

Dataset: The Pile

Neuron 3587 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: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: 0.0000

Data Index: 1726916 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0347. Min Act: 0.0000

Data Index: 773399 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0347. Min Act: 0.0000

Data Index: 896344 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1693972 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1163270 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0339. Min Act: 0.0000

Data Index: 610467 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0338. Min Act: 0.0000

Data Index: 1374588 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0337. Min Act: 0.0000

Data Index: 1932035 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0348. Min Act: 0.0000

Data Index: 248749 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0334. Min Act: 0.0000

Data Index: 571177 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0330. Min Act: 0.0000

Data Index: 1357449 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0329. Min Act: 0.0000

Data Index: 819195 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1543199 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0325. Min Act: 0.0000

Data Index: 1639552 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: 0.0001

Data Index: 45260 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0325. Min Act: 0.0000

Data Index: 1363564 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: 0.0000

Data Index: 1584829 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0312. Min Act: -0.0000

Data Index: 572552 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1975298 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1924576 (The Pile)

Max Activating Token Index: 5