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

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

Neuron 3532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1535830 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.7028. Min Act: -0.0000

Data Index: 446706 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.7185. Min Act: -0.0000

Data Index: 263749 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.7116. Min Act: -0.0000

Data Index: 238318 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.6321. Min Act: -0.0000

Data Index: 110086 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1528515 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1459740 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1617224 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1433106 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1288660 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5440. Min Act: -0.0000

Data Index: 420459 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1070804 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5401. Min Act: -0.0000

Data Index: 721466 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5180. Min Act: -0.0000

Data Index: 492583 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1467521 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.4986. Min Act: -0.0000

Data Index: 659591 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1626760 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.5264. Min Act: -0.0000

Data Index: 936598 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1540453 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.7185. Min Range: -0.7185

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1572806 (Python Code)

Max Activating Token Index: 735