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

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

Neuron 4574 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.3369. Min Act: 0.0000

Data Index: 194460 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1139969 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2984. Min Act: -0.0000

Data Index: 19184 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2938. Min Act: -0.0000

Data Index: 430868 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2842. Min Act: -0.0000

Data Index: 805219 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2829. Min Act: 0.0001

Data Index: 731280 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1285698 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2936. Min Act: -0.0000

Data Index: 960003 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2890. Min Act: -0.0000

Data Index: 691486 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2764. Min Act: -0.0000

Data Index: 791797 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2665. Min Act: -0.0000

Data Index: 28182 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1235815 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1249716 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2541. Min Act: 0.0001

Data Index: 210720 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2631. Min Act: 0.0000

Data Index: 1351473 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2581. Min Act: -0.0000

Data Index: 707574 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2529. Min Act: -0.0000

Data Index: 179510 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2484. Min Act: 0.0000

Data Index: 655720 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2407. Min Act: -0.0000

Data Index: 650970 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.3369. Min Range: -0.3369

Max Act: 0.2419. Min Act: -0.0000

Data Index: 168551 (C4 (Web Text))

Max Activating Token Index: 801