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

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

Neuron 4984 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.6176. Min Act: -0.0001

Data Index: 877153 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.3056. Min Act: -0.0001

Data Index: 77832 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2822. Min Act: -0.0001

Data Index: 454094 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1896. Min Act: -0.0001

Data Index: 973600 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2776. Min Act: -0.0001

Data Index: 147462 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2876. Min Act: -0.0001

Data Index: 838041 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2859. Min Act: -0.0001

Data Index: 434488 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2434. Min Act: -0.0001

Data Index: 1010775 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.0975. Min Act: -0.0001

Data Index: 791114 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.0792. Min Act: -0.0001

Data Index: 237597 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.2043. Min Act: -0.0001

Data Index: 354522 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1918. Min Act: -0.0001

Data Index: 563262 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1579. Min Act: -0.0001

Data Index: 237715 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1594. Min Act: -0.0001

Data Index: 1327979 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1725. Min Act: -0.0001

Data Index: 183663 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.6176. Min Range: -3.6176

Max Act: 2.9873. Min Act: -0.0001

Data Index: 850734 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1271. Min Act: -0.0001

Data Index: 871659 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1125. Min Act: -0.0001

Data Index: 727087 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.1961. Min Act: -0.0001

Data Index: 1349138 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 3.6176. Min Range: -3.6176

Max Act: 3.0956. Min Act: -0.0001

Data Index: 965882 (C4 (Web Text))

Max Activating Token Index: 11