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

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

Neuron 3170 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: 0.6684. Min Range: -0.6684

Max Act: 0.6684. Min Act: -0.0000

Data Index: 232433 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5472. Min Act: -0.0000

Data Index: 565637 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5501. Min Act: -0.0000

Data Index: 165875 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5194. Min Act: -0.0000

Data Index: 460053 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4921. Min Act: -0.0000

Data Index: 238612 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5094. Min Act: -0.0000

Data Index: 659160 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1146933 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4666. Min Act: -0.0000

Data Index: 542380 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4737. Min Act: -0.0000

Data Index: 235312 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4718. Min Act: -0.0000

Data Index: 240227 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4750. Min Act: -0.0000

Data Index: 105041 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4770. Min Act: -0.0000

Data Index: 103566 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4544. Min Act: -0.0000

Data Index: 150781 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4473. Min Act: -0.0000

Data Index: 882784 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1003973 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4466. Min Act: -0.0000

Data Index: 498805 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1090300 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4336. Min Act: -0.0000

Data Index: 637213 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1165899 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1150316 (C4 (Web Text))

Max Activating Token Index: 71