Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1368 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1532724 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0324. Min Act: -0.0002

Data Index: 742863 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0315. Min Act: -0.0002

Data Index: 355864 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1226020 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1632478 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0313. Min Act: -0.0002

Data Index: 501401 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1585715 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0300. Min Act: -0.0002

Data Index: 697818 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0294. Min Act: -0.0002

Data Index: 616874 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0294. Min Act: -0.0002

Data Index: 199201 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0299. Min Act: -0.0002

Data Index: 26083 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1020643 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0273. Min Act: -0.0002

Data Index: 804523 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1498313 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0272. Min Act: -0.0002

Data Index: 530328 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 740024 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 756651 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 804685 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 89979 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0002

Data Index: 213013 (C4 (Web Text))

Max Activating Token Index: 2