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

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

Neuron 24 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.6248. Min Act: -0.0000

Data Index: 20795 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5295. Min Act: -0.0000

Data Index: 826434 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5653. Min Act: -0.0000

Data Index: 764166 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5466. Min Act: -0.0000

Data Index: 619286 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5074. Min Act: -0.0000

Data Index: 687010 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1278800 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5263. Min Act: -0.0000

Data Index: 539071 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5614. Min Act: -0.0000

Data Index: 176275 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5601. Min Act: -0.0000

Data Index: 735516 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4573. Min Act: -0.0000

Data Index: 236998 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5037. Min Act: -0.0000

Data Index: 2146 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4902. Min Act: -0.0000

Data Index: 722461 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5065. Min Act: -0.0000

Data Index: 907060 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5055. Min Act: -0.0000

Data Index: 249416 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5195. Min Act: -0.0000

Data Index: 508416 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5004. Min Act: -0.0000

Data Index: 929017 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4793. Min Act: -0.0000

Data Index: 253288 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4656. Min Act: -0.0000

Data Index: 816166 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5123. Min Act: -0.0000

Data Index: 610787 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1275323 (C4 (Web Text))

Max Activating Token Index: 427