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

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

Neuron 2869 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8563. Min Act: -0.0000

Data Index: 336516 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7963. Min Act: -0.0000

Data Index: 792000 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7126. Min Act: -0.0000

Data Index: 366772 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6606. Min Act: -0.0000

Data Index: 234340 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1329045 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6878. Min Act: -0.0000

Data Index: 784586 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1264105 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1501164 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6271. Min Act: -0.0000

Data Index: 347026 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5188. Min Act: -0.0000

Data Index: 226958 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1271604 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6690. Min Act: -0.0000

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6387. Min Act: -0.0000

Data Index: 199845 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1655440 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5853. Min Act: -0.0000

Data Index: 373871 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1246627 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1111632 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1098897 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.5584. Min Act: -0.0000

Data Index: 976462 (C4 (Web Text))

Max Activating Token Index: 531