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

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

Neuron 2536 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1175652 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0963. Min Act: -0.0001

Data Index: 801964 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0880. Min Act: -0.0001

Data Index: 275638 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0908. Min Act: -0.0001

Data Index: 35141 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0929. Min Act: -0.0001

Data Index: 467515 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0920. Min Act: -0.0001

Data Index: 146952 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0891. Min Act: -0.0001

Data Index: 807461 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0790. Min Act: -0.0001

Data Index: 923431 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1194376 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0787. Min Act: -0.0001

Data Index: 312364 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0722. Min Act: -0.0001

Data Index: 235662 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0791. Min Act: -0.0001

Data Index: 253623 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0749. Min Act: -0.0001

Data Index: 793511 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0713. Min Act: -0.0001

Data Index: 875260 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1353953 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0741. Min Act: -0.0001

Data Index: 602542 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0724. Min Act: -0.0001

Data Index: 155524 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1122401 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1413295 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0732. Min Act: -0.0001

Data Index: 523259 (C4 (Web Text))

Max Activating Token Index: 663