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

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

Neuron 5295 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1506090 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1203738 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5096. Min Act: -0.0000

Data Index: 107661 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5287. Min Act: -0.0000

Data Index: 658328 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5091. Min Act: -0.0000

Data Index: 281282 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5005. Min Act: -0.0000

Data Index: 113947 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4828. Min Act: -0.0000

Data Index: 715085 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5108. Min Act: -0.0000

Data Index: 707780 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5095. Min Act: -0.0000

Data Index: 230314 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4747. Min Act: -0.0000

Data Index: 868513 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4645. Min Act: -0.0000

Data Index: 598356 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4629. Min Act: -0.0000

Data Index: 926020 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1322036 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1203185 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1089877 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1533697 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4619. Min Act: -0.0000

Data Index: 906620 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4769. Min Act: -0.0000

Data Index: 684899 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4626. Min Act: -0.0000

Data Index: 594778 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4556. Min Act: -0.0000

Data Index: 968175 (C4 (Web Text))

Max Activating Token Index: 141