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

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

Neuron 3934 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: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1656074 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1026. Min Act: -0.0000

Data Index: 979052 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1037. Min Act: -0.0000

Data Index: 779429 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0973. Min Act: -0.0000

Data Index: 207277 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1011. Min Act: -0.0000

Data Index: 115235 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0830. Min Act: -0.0000

Data Index: 450202 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0855. Min Act: -0.0000

Data Index: 256470 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1538131 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0930. Min Act: -0.0000

Data Index: 153064 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1508350 (Python Code)

Max Activating Token Index: 986

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1622722 (Python Code)

Max Activating Token Index: 761

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1292404 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1408692 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1464521 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0809. Min Act: -0.0000

Data Index: 395902 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0804. Min Act: -0.0000

Data Index: 668876 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1240492 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0762. Min Act: -0.0000

Data Index: 103365 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0828. Min Act: -0.0000

Data Index: 766254 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0815. Min Act: -0.0000

Data Index: 156716 (C4 (Web Text))

Max Activating Token Index: 973