Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1733 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0006

Data Index: 668238 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1246185 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0006

Data Index: 585040 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0006

Data Index: 47752 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1624355 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0006

Data Index: 529818 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 453642 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 253603 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 130286 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0006

Data Index: 848568 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1126812 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 114482 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1249380 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0006

Data Index: 378762 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0006

Data Index: 20163 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0006

Data Index: 353424 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1359496 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0006

Data Index: 617267 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0006

Data Index: 490953 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0006

Data Index: 188895 (C4 (Web Text))

Max Activating Token Index: 620