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

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

Neuron 3780 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: 1.8914. Min Range: -1.8914

Max Act: 1.7896. Min Act: -0.0000

Data Index: 655754 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.8914. Min Act: -0.0000

Data Index: 438107 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1214661 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.7295. Min Act: -0.0000

Data Index: 275321 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.6839. Min Act: -0.0001

Data Index: 161629 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.6557. Min Act: -0.0000

Data Index: 24465 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.5894. Min Act: -0.0000

Data Index: 459438 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.4839. Min Act: -0.0000

Data Index: 495740 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.3306. Min Act: -0.0000

Data Index: 987091 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.4898. Min Act: -0.0000

Data Index: 313727 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1333679 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.2884. Min Act: -0.0000

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1052476 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.4023. Min Act: -0.0000

Data Index: 259469 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1049247 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.2192. Min Act: -0.0001

Data Index: 177032 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1090439 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.1402. Min Act: -0.0000

Data Index: 641978 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.3576. Min Act: -0.0000

Data Index: 257623 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.8914. Min Range: -1.8914

Max Act: 1.1283. Min Act: -0.0000

Data Index: 468649 (C4 (Web Text))

Max Activating Token Index: 549