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

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

Neuron 4324 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3278. Min Range: -4.3278

Max Act: 4.3278. Min Act: -0.0000

Data Index: 48424 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 4.3278. Min Range: -4.3278

Max Act: 4.3052. Min Act: -0.0000

Data Index: 536744 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 4.3278. Min Range: -4.3278

Max Act: 4.1121. Min Act: -0.0000

Data Index: 111345 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.7968. Min Act: -0.0000

Data Index: 433771 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.9063. Min Act: -0.0000

Data Index: 575783 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.6107. Min Act: -0.0000

Data Index: 178647 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.5663. Min Act: -0.0000

Data Index: 61283 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.9005. Min Act: -0.0000

Data Index: 343695 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.8680. Min Act: -0.0000

Data Index: 888840 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.6824. Min Act: -0.0000

Data Index: 454770 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.6462. Min Act: -0.0000

Data Index: 935472 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.4302. Min Act: -0.0000

Data Index: 913591 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.7171. Min Act: -0.0000

Data Index: 35347 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.6838. Min Act: -0.0000

Data Index: 282147 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.4723. Min Act: -0.0000

Data Index: 798742 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.5900. Min Act: -0.0000

Data Index: 324829 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.2887. Min Act: -0.0000

Data Index: 556240 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.2763. Min Act: -0.0000

Data Index: 116137 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1110362 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 4.3278. Min Range: -4.3278

Max Act: 3.5215. Min Act: -0.0000

Data Index: 522039 (C4 (Web Text))

Max Activating Token Index: 309