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

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

Neuron 3828 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.2182. Min Act: -0.0000

Data Index: 190002 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1966. Min Act: -0.0000

Data Index: 926269 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1590280 (Python Code)

Max Activating Token Index: 156

Text #3

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9970. Min Act: -0.0000

Data Index: 941106 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1583292 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0400. Min Act: -0.0000

Data Index: 746335 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9308. Min Act: -0.0000

Data Index: 111144 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1200517 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9909. Min Act: -0.0000

Data Index: 303713 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9694. Min Act: -0.0000

Data Index: 391108 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9395. Min Act: -0.0000

Data Index: 252439 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9694. Min Act: -0.0000

Data Index: 789007 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1369032 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1256263 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8816. Min Act: -0.0000

Data Index: 940547 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8989. Min Act: -0.0000

Data Index: 252603 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8641. Min Act: -0.0000

Data Index: 656811 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8792. Min Act: -0.0000

Data Index: 422716 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1400443 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8266. Min Act: -0.0000

Data Index: 167844 (C4 (Web Text))

Max Activating Token Index: 748