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

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

Neuron 3213 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: 7.8263. Min Range: -7.8263

Max Act: 7.8263. Min Act: -0.0000

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 7.8263. Min Range: -7.8263

Max Act: 7.4510. Min Act: 0.0000

Data Index: 1111074 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.6721. Min Act: -0.0000

Data Index: 901160 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 7.8263. Min Range: -7.8263

Max Act: 7.1884. Min Act: -0.0000

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 7.8263. Min Range: -7.8263

Max Act: 7.1177. Min Act: -0.0000

Data Index: 1086319 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.7452. Min Act: 0.0000

Data Index: 211133 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.7520. Min Act: 0.0000

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.8488. Min Act: -0.0000

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.8116. Min Act: -0.0000

Data Index: 1039265 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.7781. Min Act: -0.0000

Data Index: 973893 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.8612. Min Act: 0.0001

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.4306. Min Act: -0.0000

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.2308. Min Act: -0.0000

Data Index: 265309 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.1562. Min Act: -0.0000

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.3309. Min Act: 0.0001

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.2715. Min Act: 0.0000

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 7.8263. Min Range: -7.8263

Max Act: 5.3244. Min Act: -0.0000

Data Index: 1191023 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.2142. Min Act: -0.0000

Data Index: 924196 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.1871. Min Act: -0.0000

Data Index: 566994 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 7.8263. Min Range: -7.8263

Max Act: 6.3521. Min Act: -0.0000

Data Index: 790687 (C4 (Web Text))

Max Activating Token Index: 637