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

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

Neuron 5078 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1424481 (Python Code)

Max Activating Token Index: 567

Text #1

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1642696 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1367463 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1628826 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7114. Min Act: -0.0000

Data Index: 434641 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1449447 (Python Code)

Max Activating Token Index: 464

Text #6

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1361962 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1482550 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1512611 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1406313 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6194. Min Act: -0.0000

Data Index: 750264 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6143. Min Act: 0.0000

Data Index: 1591113 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1509164 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1504365 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1530108 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1585314 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1463319 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1308374 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1425664 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1552159 (Python Code)

Max Activating Token Index: 716