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

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

Neuron 4828 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: 1.7052. Min Range: -1.7052

Max Act: 1.7052. Min Act: -0.0000

Data Index: 441756 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1328319 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.2773. Min Act: -0.0000

Data Index: 72402 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1180656 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.1742. Min Act: -0.0000

Data Index: 458738 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.0137. Min Act: -0.0000

Data Index: 400266 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.0087. Min Act: -0.0000

Data Index: 84882 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.0187. Min Act: -0.0000

Data Index: 451133 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.9437. Min Act: -0.0000

Data Index: 183759 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1248707 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1244857 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.9198. Min Act: -0.0000

Data Index: 396901 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8633. Min Act: -0.0000

Data Index: 430081 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8518. Min Act: -0.0000

Data Index: 483427 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1002659 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8688. Min Act: -0.0000

Data Index: 334499 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1033521 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8632. Min Act: -0.0000

Data Index: 941528 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.8264. Min Act: -0.0000

Data Index: 471012 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.7052. Min Range: -1.7052

Max Act: 0.7720. Min Act: 0.0000

Data Index: 769096 (C4 (Web Text))

Max Activating Token Index: 60