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

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

Neuron 3571 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: 6.1978. Min Range: -6.1978

Max Act: 6.1978. Min Act: -0.0000

Data Index: 911192 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.7320. Min Act: -0.0000

Data Index: 530832 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.3814. Min Act: -0.0000

Data Index: 225533 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.3572. Min Act: -0.0000

Data Index: 150480 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.1988. Min Act: -0.0000

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.3697. Min Act: -0.0000

Data Index: 688417 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.1375. Min Act: -0.0000

Data Index: 755929 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.7386. Min Act: -0.0000

Data Index: 24895 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.0677. Min Act: -0.0000

Data Index: 1268737 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.6117. Min Act: -0.0000

Data Index: 102488 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.5465. Min Act: -0.0000

Data Index: 65545 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 6.1978. Min Range: -6.1978

Max Act: 5.0561. Min Act: -0.0000

Data Index: 453011 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.8458. Min Act: -0.0000

Data Index: 1121893 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.6659. Min Act: -0.0000

Data Index: 25121 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.2956. Min Act: -0.0000

Data Index: 130647 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.8246. Min Act: -0.0000

Data Index: 168813 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.7818. Min Act: -0.0000

Data Index: 128537 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.7838. Min Act: -0.0000

Data Index: 266894 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.5680. Min Act: -0.0000

Data Index: 554428 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 6.1978. Min Range: -6.1978

Max Act: 4.5371. Min Act: -0.0000

Data Index: 629349 (C4 (Web Text))

Max Activating Token Index: 964