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

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

Neuron 3405 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.2505. Min Act: -0.0001

Data Index: 329017 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.8849. Min Act: -0.0001

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.8319. Min Act: -0.0001

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7572. Min Act: -0.0001

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7601. Min Act: -0.0001

Data Index: 289791 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7847. Min Act: -0.0001

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7898. Min Act: -0.0001

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1019782 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7258. Min Act: -0.0001

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.6693. Min Act: -0.0001

Data Index: 274499 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7264. Min Act: -0.0001

Data Index: 956624 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7078. Min Act: -0.0001

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7382. Min Act: -0.0001

Data Index: 153652 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.6999. Min Act: -0.0001

Data Index: 1049271 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.6966. Min Act: -0.0001

Data Index: 970387 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7582. Min Act: -0.0001

Data Index: 89572 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7047. Min Act: -0.0001

Data Index: 95992 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1043226 (C4 (Web Text))

Max Activating Token Index: 141