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

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

Neuron 3936 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1425084 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1624789 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6722. Min Act: -0.0000

Data Index: 849440 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6671. Min Act: -0.0000

Data Index: 355908 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1421988 (Python Code)

Max Activating Token Index: 533

Text #5

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1516351 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1597488 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1408799 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1651236 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6175. Min Act: -0.0000

Data Index: 790425 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1624724 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1480812 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1390658 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1148692 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1544284 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5813. Min Act: -0.0000

Data Index: 206346 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1441450 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1312616 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1470037 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1569235 (Python Code)

Max Activating Token Index: 127