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

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

Neuron 1986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2857. Min Range: -2.2857

Max Act: 2.2857. Min Act: -0.0000

Data Index: 913062 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 2.2857. Min Range: -2.2857

Max Act: 2.0179. Min Act: -0.0000

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 2.2857. Min Range: -2.2857

Max Act: 2.0468. Min Act: -0.0000

Data Index: 399566 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.9282. Min Act: -0.0000

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.8984. Min Act: -0.0000

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.7863. Min Act: -0.0000

Data Index: 1243004 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.6804. Min Act: -0.0000

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.5995. Min Act: -0.0000

Data Index: 1349804 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.5620. Min Act: -0.0000

Data Index: 556270 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1277094 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3526. Min Act: -0.0000

Data Index: 370198 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1287009 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.4259. Min Act: -0.0000

Data Index: 77962 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3714. Min Act: -0.0000

Data Index: 142028 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.4366. Min Act: -0.0000

Data Index: 1011150 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3288. Min Act: -0.0000

Data Index: 723335 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3659. Min Act: -0.0000

Data Index: 744493 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3834. Min Act: -0.0000

Data Index: 896230 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 2.2857. Min Range: -2.2857

Max Act: 1.3140. Min Act: -0.0000

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 279