Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6624. Min Act: -0.0003

Data Index: 924212 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7282. Min Act: -0.0003

Data Index: 1206753 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7166. Min Act: -0.0003

Data Index: 1287405 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6328. Min Act: -0.0003

Data Index: 425651 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6444. Min Act: -0.0003

Data Index: 1155852 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6040. Min Act: -0.0003

Data Index: 761690 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6223. Min Act: -0.0003

Data Index: 1179667 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6013. Min Act: -0.0003

Data Index: 789569 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5801. Min Act: -0.0003

Data Index: 480921 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5675. Min Act: -0.0003

Data Index: 16794 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6336. Min Act: -0.0003

Data Index: 798024 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6079. Min Act: -0.0003

Data Index: 649824 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6076. Min Act: -0.0003

Data Index: 252102 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5647. Min Act: -0.0003

Data Index: 1098362 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5836. Min Act: -0.0003

Data Index: 1040429 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5627. Min Act: -0.0003

Data Index: 654936 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5809. Min Act: -0.0003

Data Index: 218777 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5800. Min Act: -0.0003

Data Index: 81693 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5953. Min Act: -0.0003

Data Index: 1242046 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5589. Min Act: -0.0003

Data Index: 829634 (C4 (Web Text))

Max Activating Token Index: 9