Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3742 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1026758 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1194748 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6893. Min Act: -0.0001

Data Index: 455214 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6986. Min Act: -0.0001

Data Index: 421930 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6545. Min Act: -0.0001

Data Index: 630818 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6408. Min Act: -0.0001

Data Index: 313312 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6404. Min Act: -0.0001

Data Index: 1175454 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1049004 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5682. Min Act: -0.0001

Data Index: 687787 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1313873 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6491. Min Act: -0.0001

Data Index: 352242 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6038. Min Act: -0.0001

Data Index: 1336498 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5949. Min Act: -0.0001

Data Index: 174304 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6082. Min Act: -0.0001

Data Index: 658018 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5605. Min Act: -0.0001

Data Index: 1166845 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1038940 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5728. Min Act: -0.0001

Data Index: 557431 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5875. Min Act: -0.0001

Data Index: 1229078 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5813. Min Act: -0.0001

Data Index: 204921 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5639. Min Act: -0.0001

Data Index: 962562 (C4 (Web Text))

Max Activating Token Index: 588