Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2646 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.8601. Min Act: -0.0001

Data Index: 678047 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.6626. Min Act: -0.0001

Data Index: 972644 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.7446. Min Act: -0.0001

Data Index: 291806 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.7171. Min Act: -0.0001

Data Index: 1358829 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.5982. Min Act: -0.0001

Data Index: 954577 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.6519. Min Act: -0.0001

Data Index: 537724 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.7367. Min Act: -0.0001

Data Index: 552041 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4874. Min Act: -0.0001

Data Index: 57392 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4958. Min Act: -0.0001

Data Index: 1338648 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.5365. Min Act: -0.0001

Data Index: 1121235 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4741. Min Act: -0.0001

Data Index: 969033 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4552. Min Act: -0.0001

Data Index: 379996 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4571. Min Act: -0.0001

Data Index: 948409 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.5072. Min Act: -0.0001

Data Index: 372239 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4536. Min Act: -0.0001

Data Index: 326748 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4272. Min Act: -0.0001

Data Index: 534881 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4762. Min Act: -0.0001

Data Index: 581330 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.5265. Min Act: -0.0001

Data Index: 119048 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.4684. Min Act: -0.0001

Data Index: 561641 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.8601. Min Range: -1.8601

Max Act: 1.3272. Min Act: -0.0001

Data Index: 457497 (C4 (Web Text))

Max Activating Token Index: 973