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

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

Neuron 864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.1224. Min Act: -0.0000

Data Index: 440046 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0713. Min Act: -0.0000

Data Index: 651290 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1085413 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9652. Min Act: -0.0000

Data Index: 333525 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9393. Min Act: -0.0000

Data Index: 525093 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1249780 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8998. Min Act: -0.0000

Data Index: 121990 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9450. Min Act: -0.0000

Data Index: 492830 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1321284 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1148201 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1257745 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8190. Min Act: -0.0000

Data Index: 55252 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1145861 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8373. Min Act: -0.0000

Data Index: 894681 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8379. Min Act: -0.0000

Data Index: 238793 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.7858. Min Act: -0.0000

Data Index: 31498 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.7771. Min Act: -0.0000

Data Index: 48205 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8297. Min Act: -0.0000

Data Index: 415239 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.7745. Min Act: -0.0000

Data Index: 74682 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1184599 (C4 (Web Text))

Max Activating Token Index: 708