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

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

Neuron 27 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.5822. Min Act: -0.0001

Data Index: 850444 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.2305. Min Act: -0.0001

Data Index: 155107 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.1522. Min Act: -0.0001

Data Index: 491709 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.9165. Min Act: -0.0001

Data Index: 36547 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.9120. Min Act: -0.0001

Data Index: 298355 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.4663. Min Act: -0.0001

Data Index: 516614 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.5045. Min Act: -0.0001

Data Index: 1096902 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.9981. Min Act: -0.0001

Data Index: 1255728 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.0532. Min Act: -0.0001

Data Index: 1357847 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.1561. Min Act: -0.0001

Data Index: 567180 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 3.5822. Min Range: -3.5822

Max Act: 3.0376. Min Act: -0.0001

Data Index: 1256165 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.7534. Min Act: -0.0001

Data Index: 318144 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.2569. Min Act: -0.0001

Data Index: 183994 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.5381. Min Act: -0.0001

Data Index: 858507 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.7193. Min Act: -0.0001

Data Index: 1034522 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.4878. Min Act: -0.0001

Data Index: 196614 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.4744. Min Act: -0.0001

Data Index: 643166 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.8594. Min Act: -0.0001

Data Index: 454976 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.7571. Min Act: -0.0001

Data Index: 1187872 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.5822. Min Range: -3.5822

Max Act: 2.2405. Min Act: -0.0001

Data Index: 1043674 (C4 (Web Text))

Max Activating Token Index: 374