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

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

Neuron 653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.5296. Min Act: -0.0001

Data Index: 1210310 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6937. Min Act: -0.0001

Data Index: 1248509 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1094092 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.5008. Min Act: -0.0001

Data Index: 406595 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1330547 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.4070. Min Act: -0.0001

Data Index: 1334539 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.5280. Min Act: -0.0000

Data Index: 511222 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2954. Min Act: -0.0001

Data Index: 1037329 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2622. Min Act: -0.0001

Data Index: 1338566 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3797. Min Act: -0.0001

Data Index: 1215944 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0807. Min Act: -0.0001

Data Index: 938976 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2089. Min Act: -0.0001

Data Index: 128054 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0791. Min Act: -0.0001

Data Index: 1274946 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0734. Min Act: -0.0001

Data Index: 87340 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1528. Min Act: -0.0001

Data Index: 908647 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2188. Min Act: -0.0001

Data Index: 541045 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0748. Min Act: -0.0001

Data Index: 807135 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1267. Min Act: -0.0001

Data Index: 335955 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1212. Min Act: -0.0001

Data Index: 125995 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0629. Min Act: -0.0001

Data Index: 574785 (C4 (Web Text))

Max Activating Token Index: 66