Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.7072. Min Act: -0.0001

Data Index: 1114356 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.6400. Min Act: -0.0001

Data Index: 681174 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.6293. Min Act: -0.0001

Data Index: 46757 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5379. Min Act: -0.0001

Data Index: 1203596 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.6198. Min Act: -0.0001

Data Index: 1000127 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.4893. Min Act: -0.0001

Data Index: 294574 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5194. Min Act: -0.0001

Data Index: 460625 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3897. Min Act: -0.0001

Data Index: 826046 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.4023. Min Act: -0.0001

Data Index: 142163 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.1894. Min Act: -0.0001

Data Index: 1205314 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.4286. Min Act: -0.0001

Data Index: 1144833 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3395. Min Act: -0.0001

Data Index: 259600 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3795. Min Act: -0.0001

Data Index: 1119418 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3280. Min Act: -0.0001

Data Index: 656477 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1287770 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3774. Min Act: -0.0001

Data Index: 1244472 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.3178. Min Act: -0.0001

Data Index: 356179 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1074635 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.2710. Min Act: -0.0001

Data Index: 798708 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.1532. Min Act: -0.0001

Data Index: 103642 (C4 (Web Text))

Max Activating Token Index: 303