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

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

Neuron 2497 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6772. Min Act: -0.0001

Data Index: 162848 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6405. Min Act: -0.0001

Data Index: 1298348 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.5218. Min Act: -0.0001

Data Index: 952026 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1614117 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.4409. Min Act: -0.0001

Data Index: 427107 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1076568 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.4026. Min Act: -0.0001

Data Index: 763570 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3603. Min Act: -0.0001

Data Index: 185148 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1200724 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1118784 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1340182 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1593560 (Python Code)

Max Activating Token Index: 433

Text #12

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3727. Min Act: -0.0001

Data Index: 237732 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1091844 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3665. Min Act: -0.0001

Data Index: 1524089 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1613976 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3236. Min Act: -0.0001

Data Index: 313531 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3684. Min Act: -0.0001

Data Index: 26659 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3216. Min Act: -0.0001

Data Index: 139986 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3265. Min Act: -0.0001

Data Index: 765707 (C4 (Web Text))

Max Activating Token Index: 237