Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.1917. Min Act: -0.0000

Data Index: 358487 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.3102. Min Act: -0.0000

Data Index: 244959 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.1804. Min Act: -0.0000

Data Index: 249261 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.5233. Min Act: -0.0000

Data Index: 1353960 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.1303. Min Act: -0.0000

Data Index: 862580 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.2562. Min Act: -0.0000

Data Index: 150345 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.2079. Min Act: -0.0000

Data Index: 1199355 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.0605. Min Act: -0.0000

Data Index: 775815 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.0246. Min Act: -0.0000

Data Index: 440378 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.3744. Min Act: -0.0000

Data Index: 999951 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.2313. Min Act: -0.0000

Data Index: 1109202 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.7850. Min Act: -0.0000

Data Index: 429307 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.1762. Min Act: -0.0000

Data Index: 319969 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.9190. Min Act: -0.0000

Data Index: 1348120 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.8154. Min Act: -0.0000

Data Index: 299993 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.8082. Min Act: -0.0000

Data Index: 536937 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.9913. Min Act: -0.0000

Data Index: 1293026 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.7640. Min Act: -0.0000

Data Index: 649589 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 2.5233. Min Range: -2.5233

Max Act: 1.7560. Min Act: -0.0000

Data Index: 137487 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 2.5233. Min Range: -2.5233

Max Act: 2.1426. Min Act: -0.0000

Data Index: 870095 (C4 (Web Text))

Max Activating Token Index: 805