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

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

Neuron 3744 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0000

Data Index: 499957 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0596. Min Act: -0.0000

Data Index: 55187 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0641. Min Act: -0.0000

Data Index: 258317 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0640. Min Act: -0.0000

Data Index: 879883 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0607. Min Act: -0.0000

Data Index: 19529 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1039101 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0537. Min Act: -0.0000

Data Index: 109942 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0550. Min Act: -0.0000

Data Index: 308271 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1600755 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0500. Min Act: -0.0000

Data Index: 898101 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0514. Min Act: -0.0000

Data Index: 890593 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0513. Min Act: -0.0000

Data Index: 905189 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0527. Min Act: -0.0000

Data Index: 534192 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0513. Min Act: -0.0000

Data Index: 732392 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0528. Min Act: -0.0000

Data Index: 180101 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1143552 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0494. Min Act: -0.0000

Data Index: 87123 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0507. Min Act: -0.0000

Data Index: 984410 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0525. Min Act: -0.0000

Data Index: 382674 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0497. Min Act: -0.0000

Data Index: 864695 (C4 (Web Text))

Max Activating Token Index: 559