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

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

Neuron 2370 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: 2.9555. Min Range: -2.9555

Max Act: 2.9555. Min Act: -0.0000

Data Index: 125770 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.5919. Min Act: -0.0000

Data Index: 1292699 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.4629. Min Act: -0.0000

Data Index: 1189555 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.4241. Min Act: -0.0000

Data Index: 884724 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.5029. Min Act: -0.0000

Data Index: 974046 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.4558. Min Act: -0.0000

Data Index: 883717 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.4323. Min Act: -0.0000

Data Index: 1235586 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.5354. Min Act: -0.0000

Data Index: 745066 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.4926. Min Act: -0.0000

Data Index: 626139 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.5234. Min Act: -0.0000

Data Index: 486603 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.6064. Min Act: -0.0000

Data Index: 160176 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.3089. Min Act: -0.0000

Data Index: 1163245 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.0601. Min Act: -0.0000

Data Index: 4925 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.3109. Min Act: -0.0000

Data Index: 194577 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.3020. Min Act: -0.0000

Data Index: 166033 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.3989. Min Act: -0.0000

Data Index: 334031 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.2636. Min Act: -0.0000

Data Index: 1142454 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.2804. Min Act: -0.0000

Data Index: 1224406 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.2684. Min Act: -0.0000

Data Index: 268817 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 2.9555. Min Range: -2.9555

Max Act: 2.2411. Min Act: -0.0000

Data Index: 672963 (C4 (Web Text))

Max Activating Token Index: 135