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

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

Neuron 2991 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: 0.0209. Min Range: -0.0209

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1437880 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0002

Data Index: 644291 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1534197 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1168394 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0206. Min Act: -0.0002

Data Index: 807786 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1570694 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0203. Min Act: -0.0002

Data Index: 295678 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0202. Min Act: -0.0002

Data Index: 959643 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0205. Min Act: -0.0002

Data Index: 813377 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0002

Data Index: 69718 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1432504 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1358838 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0200. Min Act: -0.0002

Data Index: 939150 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0199. Min Act: -0.0002

Data Index: 921815 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1641390 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0195. Min Act: -0.0002

Data Index: 543409 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1481240 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1423102 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0197. Min Act: -0.0002

Data Index: 901709 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0197. Min Act: -0.0002

Data Index: 131834 (C4 (Web Text))

Max Activating Token Index: 873