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

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

Neuron 1860 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9244. Min Range: -2.9244

Max Act: 2.9244. Min Act: -0.0000

Data Index: 125929 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 2.9244. Min Range: -2.9244

Max Act: 2.4231. Min Act: -0.0000

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 2.9244. Min Range: -2.9244

Max Act: 2.0068. Min Act: -0.0000

Data Index: 118974 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1351768 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.5346. Min Act: -0.0000

Data Index: 229212 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.3505. Min Act: -0.0000

Data Index: 443271 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.2703. Min Act: -0.0000

Data Index: 954496 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.2252. Min Act: -0.0000

Data Index: 243340 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1335184 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.1478. Min Act: -0.0000

Data Index: 696801 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1116542 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.9244. Min Range: -2.9244

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1368066 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.9718. Min Act: -0.0000

Data Index: 551839 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1575789 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.9167. Min Act: -0.0000

Data Index: 822733 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.9790. Min Act: -0.0000

Data Index: 727151 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1564733 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1592322 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1256305 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 2.9244. Min Range: -2.9244

Max Act: 0.8558. Min Act: -0.0000

Data Index: 553955 (C4 (Web Text))

Max Activating Token Index: 475