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

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

Neuron 4026 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.8562. Min Act: -0.0000

Data Index: 458085 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.8516. Min Act: -0.0000

Data Index: 594485 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.8326. Min Act: -0.0000

Data Index: 687188 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1003870 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7070. Min Act: -0.0001

Data Index: 685898 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7482. Min Act: -0.0001

Data Index: 728179 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1214729 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7594. Min Act: -0.0001

Data Index: 681811 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7575. Min Act: -0.0000

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7210. Min Act: -0.0001

Data Index: 1066106 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7297. Min Act: -0.0001

Data Index: 573868 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1265114 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.7366. Min Act: -0.0001

Data Index: 124944 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6933. Min Act: -0.0001

Data Index: 687925 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6638. Min Act: -0.0001

Data Index: 317891 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6750. Min Act: -0.0000

Data Index: 287280 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6767. Min Act: -0.0001

Data Index: 951336 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6567. Min Act: -0.0001

Data Index: 942982 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6890. Min Act: -0.0001

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 68