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

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

Neuron 2794 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: 0.4399. Min Range: -0.4399

Max Act: 0.4399. Min Act: -0.0001

Data Index: 452260 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3978. Min Act: -0.0001

Data Index: 721402 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3762. Min Act: -0.0001

Data Index: 354330 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3501. Min Act: -0.0001

Data Index: 275341 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3736. Min Act: -0.0001

Data Index: 170855 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3621. Min Act: -0.0001

Data Index: 18018 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3624. Min Act: -0.0001

Data Index: 678292 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3702. Min Act: -0.0001

Data Index: 410019 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1139376 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1059036 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3611. Min Act: -0.0001

Data Index: 846162 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3378. Min Act: -0.0001

Data Index: 385750 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3041. Min Act: -0.0000

Data Index: 392648 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1122466 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3294. Min Act: -0.0001

Data Index: 1348 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3267. Min Act: -0.0001

Data Index: 465005 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3281. Min Act: -0.0001

Data Index: 40434 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3277. Min Act: -0.0001

Data Index: 94649 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3361. Min Act: -0.0001

Data Index: 401850 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3360. Min Act: -0.0001

Data Index: 982350 (C4 (Web Text))

Max Activating Token Index: 28