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

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

Neuron 4687 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: 1.1320. Min Range: -1.1320

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1086913 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.9851. Min Act: -0.0000

Data Index: 160545 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1007324 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1135376 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8269. Min Act: -0.0000

Data Index: 765352 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8699. Min Act: -0.0000

Data Index: 689471 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8787. Min Act: -0.0000

Data Index: 517465 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8716. Min Act: -0.0000

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1155994 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1276575 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1207449 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1105477 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8128. Min Act: -0.0000

Data Index: 535249 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1486334 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7449. Min Act: -0.0000

Data Index: 448052 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1319113 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7698. Min Act: -0.0000

Data Index: 451662 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7709. Min Act: -0.0000

Data Index: 943768 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.7797. Min Act: -0.0000

Data Index: 371952 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.1320. Min Range: -1.1320

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1138627 (C4 (Web Text))

Max Activating Token Index: 715