Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0389. Min Act: -0.0000

Data Index: 688923 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8400. Min Act: -0.0000

Data Index: 934495 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8315. Min Act: -0.0000

Data Index: 74689 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8035. Min Act: -0.0000

Data Index: 512757 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8165. Min Act: -0.0000

Data Index: 375383 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7526. Min Act: -0.0000

Data Index: 932215 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1041928 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1346856 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7465. Min Act: -0.0000

Data Index: 921058 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7400. Min Act: -0.0000

Data Index: 894174 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7245. Min Act: -0.0000

Data Index: 297907 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6965. Min Act: -0.0000

Data Index: 862189 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1232834 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7328. Min Act: -0.0000

Data Index: 52028 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6706. Min Act: -0.0000

Data Index: 285456 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6673. Min Act: -0.0000

Data Index: 797872 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6525. Min Act: -0.0000

Data Index: 82959 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6718. Min Act: -0.0000

Data Index: 972976 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6883. Min Act: -0.0000

Data Index: 622868 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6853. Min Act: -0.0000

Data Index: 870836 (C4 (Web Text))

Max Activating Token Index: 585