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

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

Neuron 3918 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1541464 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.0542. Min Act: -0.0000

Data Index: 733647 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.1036. Min Act: -0.0000

Data Index: 916104 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1139745 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1031675 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.1094. Min Act: -0.0000

Data Index: 792641 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1213275 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1445249 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9460. Min Act: -0.0000

Data Index: 894194 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.3516. Min Range: -1.3516

Max Act: 1.0092. Min Act: -0.0000

Data Index: 895802 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1125969 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9161. Min Act: -0.0000

Data Index: 43079 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1052106 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9785. Min Act: -0.0000

Data Index: 414682 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.8570. Min Act: -0.0000

Data Index: 539351 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9289. Min Act: -0.0000

Data Index: 735936 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1186391 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9231. Min Act: -0.0000

Data Index: 794845 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.8914. Min Act: -0.0000

Data Index: 699611 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.3516. Min Range: -1.3516

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1172359 (C4 (Web Text))

Max Activating Token Index: 552