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

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

Neuron 2009 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: 0.8877. Min Range: -0.8877

Max Act: 0.8877. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6216. Min Act: -0.0000

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6180. Min Act: -0.0000

Data Index: 75226 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1119676 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4990. Min Act: 0.0000

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5496. Min Act: -0.0000

Data Index: 36542 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5497. Min Act: -0.0000

Data Index: 58272 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5269. Min Act: -0.0000

Data Index: 75827 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5554. Min Act: -0.0000

Data Index: 20929 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.5076. Min Act: -0.0000

Data Index: 154640 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4688. Min Act: 0.0001

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4614. Min Act: 0.0000

Data Index: 1123909 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4439. Min Act: 0.0000

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1412237 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4382. Min Act: -0.0000

Data Index: 521837 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4191. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4315. Min Act: 0.0000

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.4078. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 808