Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0003

Data Index: 116396 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0849. Min Act: -0.0003

Data Index: 183620 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0845. Min Act: -0.0003

Data Index: 141568 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1177394 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0801. Min Act: -0.0003

Data Index: 532649 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0795. Min Act: -0.0003

Data Index: 7110 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0758. Min Act: -0.0002

Data Index: 903688 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0769. Min Act: -0.0002

Data Index: 876895 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1166312 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1161243 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1019744 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0778. Min Act: -0.0003

Data Index: 844045 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0744. Min Act: -0.0003

Data Index: 382654 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0756. Min Act: -0.0002

Data Index: 573100 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0751. Min Act: -0.0002

Data Index: 903197 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0731. Min Act: -0.0002

Data Index: 983673 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1188913 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0716. Min Act: -0.0003

Data Index: 233958 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0729. Min Act: -0.0003

Data Index: 703061 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1300929 (C4 (Web Text))

Max Activating Token Index: 920