Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1284406 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1359254 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.0679. Min Act: -0.0000

Data Index: 964086 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.0629. Min Act: -0.0000

Data Index: 800308 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.0372. Min Act: -0.0000

Data Index: 740739 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.5132. Min Range: -1.5132

Max Act: 1.0067. Min Act: -0.0000

Data Index: 906169 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9943. Min Act: -0.0000

Data Index: 882307 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9887. Min Act: -0.0001

Data Index: 96504 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9483. Min Act: -0.0000

Data Index: 370045 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1226060 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9474. Min Act: -0.0000

Data Index: 4276 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9734. Min Act: -0.0000

Data Index: 573590 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9704. Min Act: -0.0000

Data Index: 420898 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9551. Min Act: -0.0000

Data Index: 80794 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9788. Min Act: -0.0000

Data Index: 252549 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1356354 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9728. Min Act: -0.0000

Data Index: 299179 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9376. Min Act: -0.0001

Data Index: 494056 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1322798 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.5132. Min Range: -1.5132

Max Act: 0.9209. Min Act: -0.0000

Data Index: 506985 (C4 (Web Text))

Max Activating Token Index: 966