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

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

Neuron 55 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5605. Min Act: -0.0001

Data Index: 344726 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5266. Min Act: -0.0000

Data Index: 86902 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1272296 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5240. Min Act: -0.0001

Data Index: 1172558 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5036. Min Act: -0.0000

Data Index: 389811 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4770. Min Act: -0.0000

Data Index: 492080 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4837. Min Act: -0.0001

Data Index: 381994 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4450. Min Act: -0.0001

Data Index: 599722 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4493. Min Act: -0.0000

Data Index: 645469 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4629. Min Act: -0.0000

Data Index: 594684 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4643. Min Act: -0.0001

Data Index: 846609 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4477. Min Act: -0.0001

Data Index: 790109 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4656. Min Act: -0.0000

Data Index: 192567 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4394. Min Act: -0.0001

Data Index: 109580 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1111998 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4051. Min Act: -0.0000

Data Index: 596769 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.3873. Min Act: -0.0001

Data Index: 180684 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.3974. Min Act: -0.0001

Data Index: 392974 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1105 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.3812. Min Act: -0.0001

Data Index: 1280372 (C4 (Web Text))

Max Activating Token Index: 447