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

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

Neuron 19 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: 0.8063. Min Range: -0.8063

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1146496 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1174623 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6960. Min Act: -0.0000

Data Index: 53598 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7096. Min Act: -0.0000

Data Index: 921619 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6563. Min Act: -0.0000

Data Index: 208050 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6665. Min Act: -0.0000

Data Index: 30023 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6457. Min Act: -0.0000

Data Index: 678457 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6314. Min Act: -0.0000

Data Index: 968857 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6101. Min Act: -0.0000

Data Index: 416938 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1209445 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5711. Min Act: -0.0000

Data Index: 744443 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5713. Min Act: -0.0000

Data Index: 564747 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5831. Min Act: -0.0000

Data Index: 119547 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5381. Min Act: -0.0000

Data Index: 677032 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5285. Min Act: -0.0000

Data Index: 798792 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5462. Min Act: -0.0000

Data Index: 508378 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5630. Min Act: -0.0000

Data Index: 182723 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5417. Min Act: -0.0000

Data Index: 377474 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5280. Min Act: -0.0000

Data Index: 284949 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5131. Min Act: -0.0000

Data Index: 537654 (C4 (Web Text))

Max Activating Token Index: 968