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

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

Neuron 4656 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.7128. Min Act: 0.0003

Data Index: 259436 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6948. Min Act: 0.0000

Data Index: 973522 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6640. Min Act: 0.0005

Data Index: 79792 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6736. Min Act: 0.0000

Data Index: 309007 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6482. Min Act: 0.0001

Data Index: 117403 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6277. Min Act: -0.0000

Data Index: 57961 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1308493 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5731. Min Act: 0.0000

Data Index: 347779 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1024383 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5989. Min Act: 0.0001

Data Index: 226227 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5582. Min Act: 0.0001

Data Index: 1311908 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5708. Min Act: 0.0000

Data Index: 1326253 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5502. Min Act: 0.0000

Data Index: 656205 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5391. Min Act: -0.0000

Data Index: 333522 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5473. Min Act: -0.0000

Data Index: 125837 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5209. Min Act: -0.0000

Data Index: 61831 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5051. Min Act: -0.0000

Data Index: 452540 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1259128 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.4987. Min Act: -0.0000

Data Index: 987574 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5049. Min Act: -0.0000

Data Index: 816361 (C4 (Web Text))

Max Activating Token Index: 695