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

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

Neuron 2356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.4070. Min Act: -0.0000

Data Index: 24633 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.2728. Min Act: -0.0000

Data Index: 714738 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.2302. Min Act: -0.0000

Data Index: 59128 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.1254. Min Act: -0.0000

Data Index: 369598 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.0189. Min Act: -0.0000

Data Index: 955134 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.4070. Min Range: -2.4070

Max Act: 2.0035. Min Act: -0.0000

Data Index: 102132 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.8778. Min Act: -0.0000

Data Index: 506571 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.9260. Min Act: -0.0000

Data Index: 688986 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.9744. Min Act: -0.0000

Data Index: 787264 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.8395. Min Act: -0.0000

Data Index: 505491 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7228. Min Act: -0.0000

Data Index: 887790 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.9194. Min Act: -0.0000

Data Index: 140788 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7087. Min Act: -0.0000

Data Index: 113567 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7626. Min Act: -0.0000

Data Index: 156865 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1226759 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7294. Min Act: -0.0000

Data Index: 683989 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7151. Min Act: -0.0000

Data Index: 317573 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.6554. Min Act: -0.0000

Data Index: 387371 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7626. Min Act: -0.0000

Data Index: 810831 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 2.4070. Min Range: -2.4070

Max Act: 1.7439. Min Act: -0.0000

Data Index: 798569 (C4 (Web Text))

Max Activating Token Index: 154