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

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

Neuron 1747 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.7654. Min Act: -0.0000

Data Index: 200402 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0783. Min Act: -0.0000

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0704. Min Act: -0.0000

Data Index: 473353 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0142. Min Act: -0.0000

Data Index: 494722 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0488. Min Act: -0.0000

Data Index: 29344 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1272628 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9528. Min Act: -0.0000

Data Index: 41038 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9917. Min Act: -0.0000

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9571. Min Act: -0.0000

Data Index: 511750 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9140. Min Act: -0.0000

Data Index: 604418 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9915. Min Act: -0.0000

Data Index: 237250 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1318476 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9744. Min Act: -0.0000

Data Index: 734773 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1117479 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9367. Min Act: -0.0000

Data Index: 235525 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1628969 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1111443 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.9335. Min Act: -0.0000

Data Index: 423743 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.8108. Min Act: -0.0000

Data Index: 878598 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.7654. Min Range: -1.7654

Max Act: 0.8315. Min Act: -0.0000

Data Index: 398646 (C4 (Web Text))

Max Activating Token Index: 502