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

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

Neuron 2543 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: 0.6504. Min Range: -0.6504

Max Act: 0.6293. Min Act: -0.0000

Data Index: 337993 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6504. Min Act: -0.0000

Data Index: 337933 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6299. Min Act: -0.0000

Data Index: 280744 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5863. Min Act: -0.0000

Data Index: 855461 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5549. Min Act: -0.0000

Data Index: 695723 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5739. Min Act: -0.0000

Data Index: 628820 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5652. Min Act: -0.0000

Data Index: 869067 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5547. Min Act: -0.0000

Data Index: 303238 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5470. Min Act: -0.0000

Data Index: 384227 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5816. Min Act: -0.0000

Data Index: 244087 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1177117 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1295827 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5049. Min Act: -0.0000

Data Index: 217752 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4896. Min Act: -0.0000

Data Index: 68124 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1485359 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4861. Min Act: -0.0000

Data Index: 577948 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1286272 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4898. Min Act: -0.0000

Data Index: 57910 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4758. Min Act: -0.0000

Data Index: 884617 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1212077 (C4 (Web Text))

Max Activating Token Index: 886