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

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

Neuron 2245 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.5228. Min Act: -0.0000

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4891. Min Act: -0.0000

Data Index: 941614 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1213537 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4780. Min Act: -0.0000

Data Index: 984667 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1044120 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4294. Min Act: -0.0000

Data Index: 382894 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3835. Min Act: -0.0000

Data Index: 227610 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3873. Min Act: -0.0000

Data Index: 696958 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3820. Min Act: -0.0000

Data Index: 764002 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3648. Min Act: -0.0000

Data Index: 811572 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3487. Min Act: -0.0000

Data Index: 661180 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3762. Min Act: -0.0000

Data Index: 914354 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3653. Min Act: -0.0000

Data Index: 378729 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3496. Min Act: -0.0000

Data Index: 288069 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3488. Min Act: -0.0000

Data Index: 276564 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1310111 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3456. Min Act: -0.0000

Data Index: 796813 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3801. Min Act: -0.0000

Data Index: 86609 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1217443 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1068029 (C4 (Web Text))

Max Activating Token Index: 74