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

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

Neuron 3863 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: 1.3198. Min Range: -1.3198

Max Act: 1.3198. Min Act: -0.0000

Data Index: 940665 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0631. Min Act: -0.0000

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9838. Min Act: -0.0000

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9213. Min Act: -0.0000

Data Index: 964357 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8946. Min Act: -0.0000

Data Index: 729884 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9068. Min Act: -0.0000

Data Index: 603122 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8967. Min Act: -0.0000

Data Index: 482605 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9680. Min Act: -0.0000

Data Index: 259780 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1046156 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9274. Min Act: -0.0000

Data Index: 466524 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1290392 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8964. Min Act: -0.0000

Data Index: 351881 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8821. Min Act: -0.0000

Data Index: 833868 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1081107 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8073. Min Act: -0.0000

Data Index: 792902 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8581. Min Act: -0.0000

Data Index: 557208 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8579. Min Act: -0.0000

Data Index: 134741 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1185542 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8299. Min Act: -0.0000

Data Index: 847046 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1160128 (C4 (Web Text))

Max Activating Token Index: 209