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

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

Neuron 4109 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.9609. Min Act: -0.0000

Data Index: 995400 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7659. Min Act: 0.0000

Data Index: 508451 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1101796 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1252791 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7998. Min Act: -0.0000

Data Index: 137090 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1026639 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7505. Min Act: 0.0000

Data Index: 426537 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1017262 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7157. Min Act: -0.0000

Data Index: 755320 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7115. Min Act: -0.0000

Data Index: 449662 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7129. Min Act: 0.0000

Data Index: 441359 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1096421 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6428. Min Act: -0.0000

Data Index: 900787 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7243. Min Act: -0.0000

Data Index: 110050 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1307588 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.7210. Min Act: -0.0000

Data Index: 830300 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6439. Min Act: -0.0000

Data Index: 810872 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6660. Min Act: -0.0000

Data Index: 544669 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6457. Min Act: 0.0000

Data Index: 364134 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.9609. Min Range: -0.9609

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1342627 (C4 (Web Text))

Max Activating Token Index: 538