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

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

Neuron 1933 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1400296 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1416497 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1552310 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1397012 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1530385 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1624151 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1448943 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1503860 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1607922 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1556230 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1481338 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1372483 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1591846 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1609820 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1368780 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1652139 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1437066 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1385702 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1635623 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 0.9231. Min Range: -0.9231

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1422882 (Python Code)

Max Activating Token Index: 958