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

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

Neuron 5907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0000

Data Index: 253746 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4479. Min Act: -0.0000

Data Index: 897586 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4145. Min Act: -0.0000

Data Index: 240526 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4640. Min Act: -0.0000

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4263. Min Act: -0.0000

Data Index: 735431 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3920. Min Act: -0.0000

Data Index: 967973 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1138231 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3764. Min Act: -0.0000

Data Index: 60723 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3747. Min Act: -0.0000

Data Index: 818262 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3877. Min Act: -0.0000

Data Index: 614949 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1324517 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3807. Min Act: -0.0000

Data Index: 315568 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3642. Min Act: -0.0000

Data Index: 757415 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1141205 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3786. Min Act: -0.0000

Data Index: 118936 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3469. Min Act: -0.0000

Data Index: 781327 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1121667 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3356. Min Act: -0.0000

Data Index: 320713 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1294409 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3546. Min Act: -0.0000

Data Index: 455156 (C4 (Web Text))

Max Activating Token Index: 737