Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0003

Data Index: 199627 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1200. Min Act: -0.0003

Data Index: 268070 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0896. Min Act: -0.0003

Data Index: 821193 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1160. Min Act: -0.0003

Data Index: 571172 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1146. Min Act: -0.0003

Data Index: 895016 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1289449 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1157. Min Act: -0.0003

Data Index: 573604 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1071. Min Act: -0.0003

Data Index: 396087 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1071. Min Act: -0.0003

Data Index: 520904 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1020. Min Act: -0.0003

Data Index: 87747 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1076380 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0928. Min Act: -0.0003

Data Index: 387057 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1280648 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1049. Min Act: -0.0003

Data Index: 127320 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0980. Min Act: -0.0003

Data Index: 1093321 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1017. Min Act: -0.0003

Data Index: 519223 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0969. Min Act: -0.0003

Data Index: 151035 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0910. Min Act: -0.0003

Data Index: 174453 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0981. Min Act: -0.0003

Data Index: 389653 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0977. Min Act: -0.0003

Data Index: 617534 (C4 (Web Text))

Max Activating Token Index: 769