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

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

Neuron 1164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0309. Min Range: -1.0309

Max Act: 1.0309. Min Act: -0.0000

Data Index: 285466 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1098877 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1322785 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8745. Min Act: -0.0000

Data Index: 157137 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8720. Min Act: -0.0000

Data Index: 605324 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8104. Min Act: -0.0000

Data Index: 131205 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1132529 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.9251. Min Act: -0.0000

Data Index: 48065 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7895. Min Act: -0.0000

Data Index: 824896 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8092. Min Act: -0.0000

Data Index: 255772 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8256. Min Act: -0.0000

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.8031. Min Act: -0.0000

Data Index: 900901 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7560. Min Act: -0.0000

Data Index: 793750 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7488. Min Act: -0.0000

Data Index: 195828 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7203. Min Act: -0.0000

Data Index: 660429 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7494. Min Act: -0.0000

Data Index: 292255 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7106. Min Act: -0.0000

Data Index: 919049 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6973. Min Act: -0.0000

Data Index: 23410 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7247. Min Act: -0.0000

Data Index: 83008 (C4 (Web Text))

Max Activating Token Index: 160