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

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

Neuron 923 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: 0.4903. Min Range: -0.4903

Max Act: 0.4903. Min Act: -0.0001

Data Index: 477850 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4481. Min Act: -0.0001

Data Index: 831072 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4341. Min Act: -0.0001

Data Index: 162905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4137. Min Act: -0.0001

Data Index: 968592 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4094. Min Act: -0.0001

Data Index: 7081 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1139862 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3748. Min Act: -0.0001

Data Index: 586977 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1513926 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3801. Min Act: -0.0001

Data Index: 342891 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3963. Min Act: -0.0001

Data Index: 336044 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1117255 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3721. Min Act: -0.0001

Data Index: 319724 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3828. Min Act: -0.0001

Data Index: 969463 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3433. Min Act: -0.0001

Data Index: 1093185 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3672. Min Act: -0.0001

Data Index: 737480 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3451. Min Act: -0.0001

Data Index: 942873 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3758. Min Act: -0.0001

Data Index: 373819 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3570. Min Act: -0.0001

Data Index: 200314 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3456. Min Act: -0.0001

Data Index: 110117 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1162166 (C4 (Web Text))

Max Activating Token Index: 25