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

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

Neuron 3687 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: 2.5758. Min Range: -2.5758

Max Act: 2.5758. Min Act: -0.0000

Data Index: 137448 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 2.5758. Min Range: -2.5758

Max Act: 2.1726. Min Act: -0.0000

Data Index: 523710 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.9765. Min Act: -0.0000

Data Index: 671833 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1183302 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1141654 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.8317. Min Act: -0.0000

Data Index: 610474 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.7427. Min Act: -0.0000

Data Index: 51659 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.8377. Min Act: -0.0000

Data Index: 291882 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.6246. Min Act: -0.0000

Data Index: 430654 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.8119. Min Act: -0.0000

Data Index: 573913 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.7613. Min Act: -0.0000

Data Index: 384841 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.6364. Min Act: -0.0000

Data Index: 426318 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1189317 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.7191. Min Act: -0.0000

Data Index: 594821 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.5516. Min Act: -0.0000

Data Index: 169559 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1170550 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1074298 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.5905. Min Act: -0.0000

Data Index: 476811 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.5313. Min Act: -0.0000

Data Index: 838302 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 2.5758. Min Range: -2.5758

Max Act: 1.7065. Min Act: -0.0000

Data Index: 131424 (C4 (Web Text))

Max Activating Token Index: 832