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

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

Neuron 3175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.1423. Min Act: -0.0000

Data Index: 210284 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0332. Min Act: -0.0000

Data Index: 214655 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1117177 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9718. Min Act: -0.0000

Data Index: 426691 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.1423. Min Range: -1.1423

Max Act: 1.0091. Min Act: -0.0000

Data Index: 777792 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1298364 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1127986 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8747. Min Act: -0.0000

Data Index: 482800 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8336. Min Act: -0.0000

Data Index: 572018 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8361. Min Act: -0.0000

Data Index: 407178 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1640890 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1428788 (Python Code)

Max Activating Token Index: 523

Text #12

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1130579 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7851. Min Act: -0.0000

Data Index: 990806 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1324560 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7607. Min Act: -0.0000

Data Index: 860996 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7257. Min Act: -0.0000

Data Index: 138019 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7742. Min Act: -0.0000

Data Index: 339221 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7963. Min Act: -0.0000

Data Index: 422749 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.1423. Min Range: -1.1423

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1454024 (Python Code)

Max Activating Token Index: 744