Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.5032. Min Act: -0.0000

Data Index: 497775 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4837. Min Act: -0.0000

Data Index: 976395 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4685. Min Act: -0.0000

Data Index: 951734 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1108712 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1315706 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4381. Min Act: -0.0000

Data Index: 709034 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1119006 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4263. Min Act: -0.0000

Data Index: 674015 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1037231 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4116. Min Act: -0.0000

Data Index: 763557 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1010939 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4348. Min Act: -0.0000

Data Index: 491732 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4496. Min Act: -0.0000

Data Index: 688869 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4233. Min Act: -0.0000

Data Index: 117926 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4192. Min Act: -0.0000

Data Index: 188093 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4313. Min Act: -0.0000

Data Index: 9541 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4057. Min Act: -0.0000

Data Index: 273094 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1001631 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1057339 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.3654. Min Act: -0.0000

Data Index: 4087 (C4 (Web Text))

Max Activating Token Index: 621