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

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

Neuron 4367 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: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0000

Data Index: 452263 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1328. Min Act: -0.0000

Data Index: 733362 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1133. Min Act: -0.0000

Data Index: 377314 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1010458 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0840. Min Act: -0.0000

Data Index: 350333 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1338809 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1423185 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0750. Min Act: -0.0000

Data Index: 593053 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0697. Min Act: 0.0000

Data Index: 1097682 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0701. Min Act: 0.0000

Data Index: 492858 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0723. Min Act: 0.0000

Data Index: 512783 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0682. Min Act: -0.0000

Data Index: 794300 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1173635 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0625. Min Act: -0.0000

Data Index: 833920 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0638. Min Act: 0.0000

Data Index: 650715 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0684. Min Act: 0.0000

Data Index: 1244669 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0644. Min Act: 0.0000

Data Index: 389843 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0593. Min Act: -0.0000

Data Index: 902019 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0597. Min Act: 0.0000

Data Index: 1035785 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1135557 (C4 (Web Text))

Max Activating Token Index: 927