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

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

Neuron 85 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: 1.5027. Min Range: -1.5027

Max Act: 1.5027. Min Act: -0.0001

Data Index: 425328 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.5027. Min Range: -1.5027

Max Act: 1.4566. Min Act: -0.0001

Data Index: 286065 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.5027. Min Range: -1.5027

Max Act: 1.3016. Min Act: -0.0001

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 1.5027. Min Range: -1.5027

Max Act: 1.0473. Min Act: -0.0001

Data Index: 538440 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.9990. Min Act: -0.0001

Data Index: 852794 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.9892. Min Act: -0.0001

Data Index: 511644 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.9685. Min Act: -0.0000

Data Index: 111756 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8824. Min Act: -0.0001

Data Index: 1215928 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.9035. Min Act: -0.0001

Data Index: 316391 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8353. Min Act: -0.0001

Data Index: 1251717 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8562. Min Act: -0.0001

Data Index: 1147050 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8413. Min Act: -0.0000

Data Index: 603731 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8427. Min Act: -0.0001

Data Index: 1117244 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.7976. Min Act: -0.0001

Data Index: 209055 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8650. Min Act: -0.0000

Data Index: 483195 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8102. Min Act: -0.0001

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.7580. Min Act: -0.0001

Data Index: 804228 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.8274. Min Act: -0.0001

Data Index: 282468 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.7992. Min Act: -0.0001

Data Index: 438151 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.5027. Min Range: -1.5027

Max Act: 0.7842. Min Act: -0.0000

Data Index: 36111 (C4 (Web Text))

Max Activating Token Index: 814