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

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

Neuron 4694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1809. Min Range: -1.1809

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1099016 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.1809. Min Range: -1.1809

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1175256 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.1809. Min Range: -1.1809

Max Act: 1.0049. Min Act: -0.0000

Data Index: 12631 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7858. Min Act: -0.0000

Data Index: 131343 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7215. Min Act: -0.0000

Data Index: 790027 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7668. Min Act: -0.0000

Data Index: 635862 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1357517 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7829. Min Act: -0.0000

Data Index: 128227 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1274230 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7473. Min Act: -0.0000

Data Index: 451886 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7319. Min Act: -0.0000

Data Index: 209404 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1144874 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7053. Min Act: -0.0000

Data Index: 348285 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.6889. Min Act: -0.0000

Data Index: 186790 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1311782 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1268683 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.6974. Min Act: -0.0000

Data Index: 254151 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.6968. Min Act: -0.0000

Data Index: 8439 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.7226. Min Act: -0.0000

Data Index: 612163 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.1809. Min Range: -1.1809

Max Act: 0.5972. Min Act: -0.0000

Data Index: 848639 (C4 (Web Text))

Max Activating Token Index: 237