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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3018 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0001

Data Index: 61871 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0378. Min Act: -0.0001

Data Index: 547921 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1040628 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1020621 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1404666 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0331. Min Act: -0.0001

Data Index: 859759 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0327. Min Act: -0.0001

Data Index: 470600 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0327. Min Act: -0.0000

Data Index: 616854 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0322. Min Act: -0.0001

Data Index: 125161 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1082241 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0315. Min Act: -0.0002

Data Index: 854995 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0312. Min Act: -0.0000

Data Index: 881709 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0308. Min Act: -0.0001

Data Index: 880022 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0292. Min Act: -0.0000

Data Index: 538513 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0302. Min Act: -0.0000

Data Index: 175340 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0301. Min Act: -0.0001

Data Index: 586864 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0300. Min Act: -0.0002

Data Index: 597466 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0301. Min Act: -0.0001

Data Index: 882818 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1150289 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0293. Min Act: -0.0002

Data Index: 8480 (C4 (Web Text))

Max Activating Token Index: 21