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

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

Neuron 2793 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7720. Min Act: 0.0000

Data Index: 400817 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.7196. Min Act: -0.0000

Data Index: 697508 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6853. Min Act: 0.0000

Data Index: 628719 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6656. Min Act: 0.0000

Data Index: 952174 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1274941 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1068856 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1059440 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6113. Min Act: -0.0000

Data Index: 537601 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6992. Min Act: -0.0000

Data Index: 900610 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5875. Min Act: -0.0000

Data Index: 851630 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6232. Min Act: -0.0000

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1267303 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5926. Min Act: -0.0000

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1107578 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1327060 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6015. Min Act: 0.0000

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5926. Min Act: -0.0000

Data Index: 479355 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6052. Min Act: -0.0000

Data Index: 370108 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.6242. Min Act: 0.0001

Data Index: 620744 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.7720. Min Range: -0.7720

Max Act: 0.5813. Min Act: 0.0000

Data Index: 179850 (C4 (Web Text))

Max Activating Token Index: 53