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

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

Neuron 4220 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: 0.3279. Min Range: -0.3279

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1280270 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.3279. Min Act: -0.0000

Data Index: 398770 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.3005. Min Act: -0.0000

Data Index: 643451 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1153143 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2806. Min Act: -0.0000

Data Index: 617842 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2797. Min Act: -0.0000

Data Index: 255254 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2882. Min Act: -0.0000

Data Index: 749421 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1169293 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2052. Min Act: -0.0000

Data Index: 746496 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1935. Min Act: -0.0000

Data Index: 776536 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2004. Min Act: -0.0000

Data Index: 350556 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2266. Min Act: -0.0000

Data Index: 891358 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1337972 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1004409 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1976. Min Act: -0.0000

Data Index: 425801 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1828. Min Act: -0.0000

Data Index: 653672 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1657. Min Act: -0.0000

Data Index: 863583 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1793. Min Act: -0.0000

Data Index: 327745 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.3279. Min Range: -0.3279

Max Act: 0.1770. Min Act: -0.0000

Data Index: 3299 (C4 (Web Text))

Max Activating Token Index: 849