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

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

Neuron 3417 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1582. Min Act: -0.0000

Data Index: 280055 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0692. Min Act: -0.0000

Data Index: 406432 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1305285 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9709. Min Act: -0.0000

Data Index: 289855 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1148741 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.7622. Min Act: -0.0000

Data Index: 710701 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.7628. Min Act: -0.0000

Data Index: 281486 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.7451. Min Act: -0.0000

Data Index: 400677 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6975. Min Act: -0.0000

Data Index: 826653 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6936. Min Act: -0.0000

Data Index: 743451 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.7164. Min Act: -0.0000

Data Index: 205552 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6843. Min Act: -0.0000

Data Index: 621819 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.7039. Min Act: -0.0000

Data Index: 230524 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1276329 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6631. Min Act: -0.0000

Data Index: 257446 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6485. Min Act: -0.0000

Data Index: 811515 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6450. Min Act: -0.0000

Data Index: 140078 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6355. Min Act: -0.0000

Data Index: 917655 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6321. Min Act: -0.0000

Data Index: 718428 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1121357 (C4 (Web Text))

Max Activating Token Index: 696