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

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

Neuron 2718 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0096. Min Range: -1.0096

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1032523 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1005243 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7119. Min Act: -0.0000

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7130. Min Act: -0.0000

Data Index: 242281 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1648503 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1114429 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6317. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6278. Min Act: -0.0000

Data Index: 497928 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6515. Min Act: -0.0000

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1656795 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1250706 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5668. Min Act: -0.0000

Data Index: 59895 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1604993 (Python Code)

Max Activating Token Index: 180

Text #13

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1475133 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6279. Min Act: -0.0000

Data Index: 147370 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1492666 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5768. Min Act: -0.0000

Data Index: 741193 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1562052 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.5337. Min Act: -0.0000

Data Index: 517220 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 998