Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1865 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1245037 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6783. Min Act: -0.0000

Data Index: 991231 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6137. Min Act: -0.0001

Data Index: 254265 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6236. Min Act: -0.0000

Data Index: 494408 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6174. Min Act: -0.0001

Data Index: 124177 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6628. Min Act: -0.0001

Data Index: 1229305 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5807. Min Act: -0.0001

Data Index: 917510 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6052. Min Act: -0.0001

Data Index: 608241 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5784. Min Act: -0.0001

Data Index: 858558 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5672. Min Act: -0.0001

Data Index: 818289 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1155195 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5516. Min Act: -0.0001

Data Index: 515812 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5496. Min Act: -0.0001

Data Index: 13895 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5872. Min Act: -0.0000

Data Index: 946101 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5449. Min Act: -0.0001

Data Index: 232980 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5410. Min Act: -0.0001

Data Index: 1099654 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5513. Min Act: -0.0000

Data Index: 167008 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5277. Min Act: -0.0000

Data Index: 162224 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5279. Min Act: -0.0001

Data Index: 101363 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.5087. Min Act: -0.0001

Data Index: 926450 (C4 (Web Text))

Max Activating Token Index: 350