Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5195 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1178. Min Range: -2.1178

Max Act: 2.0716. Min Act: -0.0000

Data Index: 271835 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.1178. Min Range: -2.1178

Max Act: 2.0058. Min Act: -0.0000

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 2.1178. Min Range: -2.1178

Max Act: 2.1178. Min Act: -0.0000

Data Index: 79911 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1061092 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.8019. Min Act: -0.0000

Data Index: 210622 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.8043. Min Act: -0.0000

Data Index: 759249 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.5875. Min Act: -0.0000

Data Index: 39972 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1134383 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.5743. Min Act: -0.0000

Data Index: 878575 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1096935 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4387. Min Act: -0.0000

Data Index: 320981 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4741. Min Act: -0.0000

Data Index: 150318 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4584. Min Act: -0.0000

Data Index: 1159119 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.3720. Min Act: -0.0000

Data Index: 186237 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1260068 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1344422 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1135049 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.4334. Min Act: -0.0000

Data Index: 759324 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.2804. Min Act: -0.0000

Data Index: 536744 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.1178. Min Range: -2.1178

Max Act: 1.3919. Min Act: -0.0000

Data Index: 570315 (C4 (Web Text))

Max Activating Token Index: 169