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

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

Neuron 4119 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: 3.7603. Min Range: -3.7603

Max Act: 3.7603. Min Act: -0.0000

Data Index: 488353 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.7468. Min Act: -0.0000

Data Index: 649191 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.6787. Min Act: 0.0000

Data Index: 1296552 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.5299. Min Act: -0.0000

Data Index: 964394 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.3333. Min Act: -0.0000

Data Index: 327998 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.2159. Min Act: 0.0000

Data Index: 1045828 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.1879. Min Act: -0.0000

Data Index: 655286 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.1662. Min Act: -0.0000

Data Index: 193064 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.9408. Min Act: -0.0000

Data Index: 63461 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.0798. Min Act: 0.0000

Data Index: 1359236 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.0752. Min Act: -0.0000

Data Index: 823049 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.0418. Min Act: -0.0000

Data Index: 408097 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.0138. Min Act: -0.0000

Data Index: 401130 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.8644. Min Act: -0.0000

Data Index: 625067 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.0000. Min Act: -0.0000

Data Index: 1066178 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.9863. Min Act: -0.0000

Data Index: 691046 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.9977. Min Act: -0.0000

Data Index: 855013 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.7603. Min Range: -3.7603

Max Act: 3.1264. Min Act: -0.0000

Data Index: 490119 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.9788. Min Act: -0.0000

Data Index: 1198791 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.7603. Min Range: -3.7603

Max Act: 2.9414. Min Act: -0.0000

Data Index: 208138 (C4 (Web Text))

Max Activating Token Index: 52