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

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

Neuron 1011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1343. Min Act: -0.0000

Data Index: 17182 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.1910. Min Act: -0.0000

Data Index: 769231 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.8875. Min Act: -0.0000

Data Index: 347559 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.1910. Min Range: -3.1910

Max Act: 3.0030. Min Act: -0.0000

Data Index: 558015 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5449. Min Act: -0.0000

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.7335. Min Act: -0.0000

Data Index: 853640 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6926. Min Act: -0.0000

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.4171. Min Act: -0.0000

Data Index: 425132 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5502. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6512. Min Act: -0.0000

Data Index: 920045 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5291. Min Act: -0.0000

Data Index: 991289 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6239. Min Act: -0.0000

Data Index: 1031940 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.6849. Min Act: -0.0000

Data Index: 996785 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.3108. Min Act: -0.0000

Data Index: 94510 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.5413. Min Act: -0.0000

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.4306. Min Act: -0.0000

Data Index: 829865 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1039606 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1355320 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.2025. Min Act: -0.0000

Data Index: 1075946 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 3.1910. Min Range: -3.1910

Max Act: 2.3852. Min Act: -0.0000

Data Index: 1027341 (C4 (Web Text))

Max Activating Token Index: 218