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

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

Neuron 4813 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: 2.4726. Min Range: -2.4726

Max Act: 2.4726. Min Act: -0.0000

Data Index: 430084 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1358778 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.8032. Min Act: -0.0000

Data Index: 260026 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1013296 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.8266. Min Act: -0.0000

Data Index: 672156 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.8035. Min Act: -0.0000

Data Index: 853091 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5572. Min Act: -0.0000

Data Index: 1033281 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.7031. Min Act: -0.0000

Data Index: 421422 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1072566 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.6622. Min Act: -0.0000

Data Index: 834802 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5776. Min Act: -0.0000

Data Index: 343587 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5316. Min Act: -0.0000

Data Index: 1059166 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.6418. Min Act: -0.0000

Data Index: 788658 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5392. Min Act: -0.0000

Data Index: 1019019 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5395. Min Act: -0.0000

Data Index: 573515 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5348. Min Act: -0.0000

Data Index: 966750 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5301. Min Act: -0.0000

Data Index: 63445 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.6020. Min Act: -0.0000

Data Index: 1279983 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.5275. Min Act: -0.0000

Data Index: 290490 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 2.4726. Min Range: -2.4726

Max Act: 1.3868. Min Act: -0.0000

Data Index: 234174 (C4 (Web Text))

Max Activating Token Index: 669