Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3316 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0000

Data Index: 681497 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0513. Min Act: -0.0000

Data Index: 78004 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0454. Min Act: -0.0000

Data Index: 866648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0473. Min Act: -0.0000

Data Index: 2665 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0550. Min Act: -0.0000

Data Index: 810086 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1041412 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0438. Min Act: -0.0000

Data Index: 586583 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0450. Min Act: -0.0000

Data Index: 118497 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0381. Min Act: -0.0000

Data Index: 34730 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0418. Min Act: -0.0000

Data Index: 249540 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0417. Min Act: -0.0000

Data Index: 612735 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1638042 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0449. Min Act: -0.0000

Data Index: 304494 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0395. Min Act: -0.0000

Data Index: 833245 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0395. Min Act: -0.0000

Data Index: 640500 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0384. Min Act: -0.0000

Data Index: 557231 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0380. Min Act: -0.0000

Data Index: 881243 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1178695 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0386. Min Act: -0.0000

Data Index: 933618 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0389. Min Act: -0.0000

Data Index: 720654 (C4 (Web Text))

Max Activating Token Index: 496