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

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

Neuron 2009 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1125540 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3468. Min Act: -0.0001

Data Index: 925752 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1055388 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3090. Min Act: -0.0001

Data Index: 1048593 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1281846 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2865. Min Act: -0.0001

Data Index: 1022005 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2997. Min Act: -0.0001

Data Index: 192436 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2900. Min Act: -0.0001

Data Index: 457425 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1161224 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1320967 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1133119 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2505. Min Act: -0.0001

Data Index: 109367 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2690. Min Act: -0.0001

Data Index: 199644 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2801. Min Act: -0.0001

Data Index: 850387 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2643. Min Act: -0.0001

Data Index: 980437 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2409. Min Act: -0.0001

Data Index: 142172 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2478. Min Act: -0.0001

Data Index: 814814 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2428. Min Act: -0.0001

Data Index: 40060 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1123468 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2487. Min Act: -0.0001

Data Index: 59054 (C4 (Web Text))

Max Activating Token Index: 448