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

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

Neuron 533 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: 1.7563. Min Range: -1.7563

Max Act: 1.7563. Min Act: -0.0000

Data Index: 887561 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1045420 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3564. Min Act: -0.0000

Data Index: 183753 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4829. Min Act: -0.0000

Data Index: 148882 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3968. Min Act: -0.0000

Data Index: 833387 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3358. Min Act: -0.0000

Data Index: 898929 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4874. Min Act: -0.0000

Data Index: 181942 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4597. Min Act: -0.0000

Data Index: 350303 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.5096. Min Act: -0.0000

Data Index: 591367 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3125. Min Act: -0.0000

Data Index: 204894 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1328058 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3252. Min Act: -0.0000

Data Index: 473328 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1263274 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2215. Min Act: -0.0000

Data Index: 137423 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.3079. Min Act: -0.0000

Data Index: 174944 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2823. Min Act: -0.0000

Data Index: 157164 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.4233. Min Act: -0.0000

Data Index: 979030 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2964. Min Act: -0.0000

Data Index: 47277 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2614. Min Act: -0.0000

Data Index: 137884 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.7563. Min Range: -1.7563

Max Act: 1.2578. Min Act: -0.0000

Data Index: 107239 (C4 (Web Text))

Max Activating Token Index: 941