Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.2771. Min Act: -0.0001

Data Index: 1037581 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.2121. Min Act: -0.0000

Data Index: 846474 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1308792 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.2067. Min Act: -0.0000

Data Index: 790523 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1179877 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1427. Min Act: -0.0000

Data Index: 836848 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1776. Min Act: -0.0000

Data Index: 643436 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1028. Min Act: -0.0000

Data Index: 475293 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1342640 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1220209 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.1152. Min Act: -0.0001

Data Index: 710320 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0522. Min Act: -0.0001

Data Index: 981159 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0129. Min Act: -0.0001

Data Index: 851498 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9752. Min Act: -0.0001

Data Index: 998991 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0316. Min Act: -0.0001

Data Index: 973405 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9909. Min Act: -0.0001

Data Index: 1426070 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9789. Min Act: -0.0001

Data Index: 1421399 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0450. Min Act: -0.0000

Data Index: 343321 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.2771. Min Range: -1.2771

Max Act: 0.9756. Min Act: -0.0000

Data Index: 174624 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.2771. Min Range: -1.2771

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1073231 (C4 (Web Text))

Max Activating Token Index: 457