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

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

Neuron 3424 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: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0000

Data Index: 152199 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0905. Min Act: -0.0000

Data Index: 579962 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0868. Min Act: -0.0000

Data Index: 222370 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0880. Min Act: -0.0000

Data Index: 178321 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1151189 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0884. Min Act: -0.0000

Data Index: 962922 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0787. Min Act: -0.0000

Data Index: 859459 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0784. Min Act: -0.0000

Data Index: 737568 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0836. Min Act: -0.0000

Data Index: 287100 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1160522 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0805. Min Act: -0.0000

Data Index: 585241 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0831. Min Act: -0.0000

Data Index: 989811 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0820. Min Act: -0.0000

Data Index: 265980 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0853. Min Act: -0.0000

Data Index: 902379 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0818. Min Act: -0.0000

Data Index: 534532 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0810. Min Act: -0.0000

Data Index: 683700 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0773. Min Act: -0.0000

Data Index: 145525 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0767. Min Act: -0.0000

Data Index: 131662 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1290025 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0805. Min Act: -0.0000

Data Index: 875935 (C4 (Web Text))

Max Activating Token Index: 271