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

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

Neuron 1576 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: 2.3577. Min Range: -2.3577

Max Act: 2.3279. Min Act: -0.0000

Data Index: 755941 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1899. Min Act: -0.0000

Data Index: 508037 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.3577. Min Act: -0.0000

Data Index: 818271 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.8809. Min Act: -0.0000

Data Index: 38946 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1668. Min Act: -0.0000

Data Index: 675279 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.0543. Min Act: -0.0000

Data Index: 379681 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.0873. Min Act: -0.0000

Data Index: 1177841 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1158841 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.2503. Min Act: -0.0000

Data Index: 496685 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1187. Min Act: -0.0000

Data Index: 965917 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1066453 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.9895. Min Act: -0.0000

Data Index: 601075 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.0769. Min Act: -0.0000

Data Index: 636184 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 2.3577. Min Range: -2.3577

Max Act: 2.1071. Min Act: -0.0000

Data Index: 906837 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.9382. Min Act: -0.0001

Data Index: 881743 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.7817. Min Act: -0.0001

Data Index: 1059331 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.9667. Min Act: -0.0000

Data Index: 140218 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.9510. Min Act: -0.0000

Data Index: 1133339 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.8384. Min Act: -0.0000

Data Index: 639661 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 2.3577. Min Range: -2.3577

Max Act: 1.8054. Min Act: -0.0000

Data Index: 34930 (C4 (Web Text))

Max Activating Token Index: 430