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

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

Neuron 1446 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5219. Min Range: -2.5219

Max Act: 2.5219. Min Act: -0.0000

Data Index: 1307549 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.5219. Min Range: -2.5219

Max Act: 2.3469. Min Act: -0.0000

Data Index: 268061 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 2.5219. Min Range: -2.5219

Max Act: 2.0739. Min Act: -0.0000

Data Index: 1354420 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.8329. Min Act: -0.0000

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.7441. Min Act: -0.0000

Data Index: 324151 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4852. Min Act: -0.0000

Data Index: 999349 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5686. Min Act: -0.0000

Data Index: 605861 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5650. Min Act: -0.0000

Data Index: 14667 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5553. Min Act: -0.0000

Data Index: 878552 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5174. Min Act: -0.0000

Data Index: 634975 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5049. Min Act: -0.0000

Data Index: 388376 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4073. Min Act: -0.0000

Data Index: 98953 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1540204 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1328984 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.3909. Min Act: -0.0000

Data Index: 226912 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4643. Min Act: -0.0000

Data Index: 431678 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1094244 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.5543. Min Act: -0.0000

Data Index: 869127 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 2.5219. Min Range: -2.5219

Max Act: 1.4715. Min Act: -0.0000

Data Index: 1151771 (C4 (Web Text))

Max Activating Token Index: 136