Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0001

Data Index: 119983 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0246. Min Act: -0.0001

Data Index: 274988 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0347. Min Act: -0.0001

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1381603 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1623467 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0284. Min Act: -0.0001

Data Index: 523359 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1563782 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0229. Min Act: -0.0001

Data Index: 678017 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0206. Min Act: -0.0001

Data Index: 293942 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0211. Min Act: -0.0001

Data Index: 127718 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0208. Min Act: -0.0001

Data Index: 219432 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1008565 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1053743 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0208. Min Act: -0.0001

Data Index: 457506 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1066670 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0181. Min Act: -0.0001

Data Index: 657985 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0204. Min Act: -0.0001

Data Index: 814360 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0192. Min Act: -0.0001

Data Index: 625549 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1535535 (Python Code)

Max Activating Token Index: 305

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0192. Min Act: -0.0001

Data Index: 652596 (C4 (Web Text))

Max Activating Token Index: 128