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

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

Neuron 1321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9868. Min Act: -0.0001

Data Index: 733365 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9521. Min Act: -0.0001

Data Index: 788990 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9447. Min Act: -0.0000

Data Index: 185262 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9261. Min Act: -0.0001

Data Index: 1023062 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8951. Min Act: -0.0000

Data Index: 200061 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9283. Min Act: -0.0000

Data Index: 563384 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8638. Min Act: -0.0001

Data Index: 206756 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8578. Min Act: -0.0001

Data Index: 41570 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9160. Min Act: -0.0001

Data Index: 138684 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8321. Min Act: -0.0001

Data Index: 1561150 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8827. Min Act: -0.0001

Data Index: 1373749 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8844. Min Act: -0.0001

Data Index: 478970 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8757. Min Act: -0.0000

Data Index: 196652 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9350. Min Act: -0.0001

Data Index: 749630 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8598. Min Act: -0.0001

Data Index: 1556529 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8333. Min Act: -0.0001

Data Index: 891982 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8672. Min Act: -0.0001

Data Index: 406061 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8252. Min Act: -0.0001

Data Index: 257335 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8277. Min Act: -0.0000

Data Index: 945237 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8467. Min Act: -0.0001

Data Index: 282472 (C4 (Web Text))

Max Activating Token Index: 236