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

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

Neuron 1795 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: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0000

Data Index: 741034 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0554. Min Act: 0.0000

Data Index: 910395 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0501. Min Act: -0.0000

Data Index: 303891 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1482163 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0467. Min Act: -0.0000

Data Index: 977837 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0409. Min Act: -0.0000

Data Index: 353482 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1327856 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0327. Min Act: -0.0000

Data Index: 660117 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0328. Min Act: -0.0000

Data Index: 219469 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1027356 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0282. Min Act: -0.0000

Data Index: 771900 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0344. Min Act: -0.0000

Data Index: 111685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1418429 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0319. Min Act: -0.0000

Data Index: 188715 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0292. Min Act: -0.0000

Data Index: 1476907 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0311. Min Act: -0.0000

Data Index: 344425 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0309. Min Act: -0.0000

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0310. Min Act: -0.0000

Data Index: 455043 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0308. Min Act: -0.0000

Data Index: 1085417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1488476 (Python Code)

Max Activating Token Index: 753