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

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

Neuron 3947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.8376. Min Act: -0.0001

Data Index: 1294600 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.6180. Min Act: -0.0001

Data Index: 49556 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.3721. Min Act: -0.0001

Data Index: 17922 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.2535. Min Act: -0.0001

Data Index: 752578 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.3697. Min Act: -0.0001

Data Index: 1042141 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.2759. Min Act: -0.0001

Data Index: 1218245 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.2544. Min Act: -0.0001

Data Index: 176704 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.2072. Min Act: -0.0001

Data Index: 474736 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.2771. Min Act: -0.0001

Data Index: 214962 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.1048. Min Act: -0.0001

Data Index: 1273852 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0492. Min Act: -0.0001

Data Index: 1318411 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0959. Min Act: -0.0001

Data Index: 418378 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0826. Min Act: -0.0001

Data Index: 716895 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0241. Min Act: -0.0001

Data Index: 597859 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0162. Min Act: -0.0001

Data Index: 756945 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0111. Min Act: -0.0001

Data Index: 750913 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 2.8376. Min Range: -2.8376

Max Act: 1.9464. Min Act: -0.0001

Data Index: 331521 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.8376. Min Range: -2.8376

Max Act: 1.9394. Min Act: -0.0001

Data Index: 452809 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0586. Min Act: -0.0001

Data Index: 916025 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.8376. Min Range: -2.8376

Max Act: 2.0503. Min Act: -0.0001

Data Index: 561284 (C4 (Web Text))

Max Activating Token Index: 17