Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.5171. Min Act: -0.0000

Data Index: 659406 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.5360. Min Act: -0.0000

Data Index: 746376 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1281965 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1134068 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1172273 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3891. Min Act: -0.0000

Data Index: 278593 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3960. Min Act: -0.0000

Data Index: 496353 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4135. Min Act: -0.0000

Data Index: 46471 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3909. Min Act: -0.0000

Data Index: 377635 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1204576 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1043973 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4182. Min Act: -0.0000

Data Index: 815585 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1133517 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4065. Min Act: -0.0000

Data Index: 100799 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1284369 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1172795 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3980. Min Act: -0.0000

Data Index: 480425 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3729. Min Act: -0.0000

Data Index: 565499 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3753. Min Act: -0.0000

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.3765. Min Act: -0.0000

Data Index: 716621 (C4 (Web Text))

Max Activating Token Index: 959