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

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

Neuron 1429 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: 0.7620. Min Range: -0.7620

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1016208 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.7159. Min Act: -0.0000

Data Index: 941700 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6929. Min Act: -0.0000

Data Index: 889176 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6814. Min Act: -0.0000

Data Index: 105720 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.6011. Min Act: -0.0000

Data Index: 430567 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5629. Min Act: -0.0000

Data Index: 37499 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5717. Min Act: -0.0000

Data Index: 142092 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5885. Min Act: -0.0000

Data Index: 152312 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1113661 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1032319 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5208. Min Act: -0.0000

Data Index: 813308 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5007. Min Act: -0.0000

Data Index: 931033 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4816. Min Act: -0.0000

Data Index: 545424 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4679. Min Act: -0.0000

Data Index: 61452 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1039803 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4906. Min Act: -0.0000

Data Index: 660845 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4732. Min Act: -0.0000

Data Index: 448674 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1137648 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4844. Min Act: -0.0000

Data Index: 243784 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4632. Min Act: -0.0000

Data Index: 396403 (C4 (Web Text))

Max Activating Token Index: 223