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

Dataset: The Pile

Neuron 1682 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: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0000

Data Index: 732037 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0373. Min Act: -0.0000

Data Index: 933325 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0368. Min Act: -0.0000

Data Index: 226803 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0364. Min Act: -0.0000

Data Index: 224640 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0359. Min Act: -0.0000

Data Index: 886383 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0356. Min Act: -0.0000

Data Index: 990146 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1415974 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1112992 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0354. Min Act: -0.0000

Data Index: 306006 (The Pile)

Max Activating Token Index: 7

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1659660 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1364416 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0350. Min Act: -0.0000

Data Index: 492955 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1266574 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0350. Min Act: -0.0000

Data Index: 550996 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0347. Min Act: -0.0000

Data Index: 54667 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1910088 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0345. Min Act: -0.0000

Data Index: 8572 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0344. Min Act: 0.0000

Data Index: 536577 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0357. Min Act: -0.0000

Data Index: 431515 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0345. Min Act: -0.0000

Data Index: 488350 (The Pile)

Max Activating Token Index: 5