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

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

Neuron 4750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1191946 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6930. Min Act: -0.0000

Data Index: 1311990 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.7457. Min Act: -0.0000

Data Index: 662499 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.7309. Min Act: -0.0000

Data Index: 832309 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.7122. Min Act: -0.0000

Data Index: 107388 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.7029. Min Act: -0.0000

Data Index: 301093 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5627. Min Act: -0.0000

Data Index: 330425 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6376. Min Act: -0.0000

Data Index: 926027 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6400. Min Act: -0.0000

Data Index: 80917 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6090. Min Act: -0.0000

Data Index: 884563 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1166031 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6684. Min Act: -0.0000

Data Index: 1185839 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5661. Min Act: -0.0000

Data Index: 679013 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4631. Min Act: -0.0000

Data Index: 74763 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1134990 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5143. Min Act: -0.0000

Data Index: 811133 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4367. Min Act: -0.0000

Data Index: 778716 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4991. Min Act: -0.0000

Data Index: 653629 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5726. Min Act: -0.0000

Data Index: 910058 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4762. Min Act: -0.0000

Data Index: 67928 (C4 (Web Text))

Max Activating Token Index: 993