Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1261. Min Act: -0.0000

Data Index: 310002 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1053. Min Act: -0.0000

Data Index: 405869 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0988. Min Act: -0.0000

Data Index: 44404 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1002. Min Act: -0.0000

Data Index: 73700 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1186389 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1320861 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1103278 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1229569 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0887. Min Act: -0.0000

Data Index: 583950 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1110559 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1080712 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1200240 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1546345 (Python Code)

Max Activating Token Index: 301

Text #13

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1388372 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1041773 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1431007 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0665. Min Act: -0.0000

Data Index: 371455 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1495759 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0560. Min Act: -0.0000

Data Index: 466776 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0654. Min Act: -0.0000

Data Index: 46625 (C4 (Web Text))

Max Activating Token Index: 224