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

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

Neuron 4504 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.9855. Min Act: -0.0000

Data Index: 466719 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1125237 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.8490. Min Act: -0.0000

Data Index: 15982 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.2768. Min Act: -0.0000

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.3817. Min Act: -0.0000

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.3259. Min Act: -0.0000

Data Index: 461714 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1101089 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.2421. Min Act: -0.0000

Data Index: 636732 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.1923. Min Act: -0.0000

Data Index: 983611 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.1611. Min Act: -0.0000

Data Index: 352253 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.0503. Min Act: -0.0000

Data Index: 285797 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.0511. Min Act: -0.0000

Data Index: 762992 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1232738 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 2.9855. Min Range: -2.9855

Max Act: 1.8877. Min Act: -0.0000

Data Index: 878486 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 2.9855. Min Range: -2.9855

Max Act: 1.9947. Min Act: -0.0000

Data Index: 997186 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.9855. Min Range: -2.9855

Max Act: 1.9837. Min Act: -0.0000

Data Index: 168659 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.0726. Min Act: -0.0000

Data Index: 855226 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 2.9855. Min Range: -2.9855

Max Act: 1.9284. Min Act: -0.0000

Data Index: 144848 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.9855. Min Range: -2.9855

Max Act: 2.0214. Min Act: -0.0000

Data Index: 1665 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.9855. Min Range: -2.9855

Max Act: 1.8891. Min Act: -0.0000

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 668