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

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

Neuron 4340 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.7358. Min Act: -0.0002

Data Index: 110867 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6625. Min Act: -0.0002

Data Index: 1282644 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6100. Min Act: -0.0002

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6286. Min Act: -0.0002

Data Index: 212850 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6057. Min Act: -0.0002

Data Index: 464644 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6001. Min Act: -0.0002

Data Index: 510239 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5848. Min Act: -0.0002

Data Index: 627607 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5915. Min Act: -0.0002

Data Index: 781533 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5698. Min Act: -0.0002

Data Index: 1288576 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5788. Min Act: -0.0002

Data Index: 636992 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5768. Min Act: -0.0002

Data Index: 1313891 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6124. Min Act: -0.0002

Data Index: 1155515 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.6332. Min Act: -0.0002

Data Index: 796423 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5411. Min Act: -0.0002

Data Index: 1070196 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5759. Min Act: -0.0002

Data Index: 765214 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5699. Min Act: -0.0002

Data Index: 1070183 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5528. Min Act: -0.0002

Data Index: 1173701 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5522. Min Act: -0.0002

Data Index: 976482 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5479. Min Act: -0.0002

Data Index: 972302 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.7358. Min Range: -0.7358

Max Act: 0.5482. Min Act: -0.0002

Data Index: 1211425 (C4 (Web Text))

Max Activating Token Index: 45