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

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

Neuron 4622 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3903. Min Range: -2.3903

Max Act: 2.3903. Min Act: -0.0000

Data Index: 1135402 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.3903. Min Range: -2.3903

Max Act: 2.2204. Min Act: -0.0000

Data Index: 248766 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 2.3903. Min Range: -2.3903

Max Act: 2.0717. Min Act: -0.0000

Data Index: 131178 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.9363. Min Act: -0.0000

Data Index: 655273 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.9262. Min Act: -0.0000

Data Index: 1189419 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.8268. Min Act: -0.0000

Data Index: 379185 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.8079. Min Act: -0.0000

Data Index: 905000 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7884. Min Act: -0.0000

Data Index: 289305 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.6908. Min Act: -0.0000

Data Index: 896711 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.8859. Min Act: -0.0000

Data Index: 541911 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.6688. Min Act: -0.0000

Data Index: 771617 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.6758. Min Act: -0.0000

Data Index: 1067095 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7293. Min Act: -0.0000

Data Index: 720153 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.6262. Min Act: -0.0000

Data Index: 166193 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7813. Min Act: -0.0000

Data Index: 789283 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7792. Min Act: -0.0000

Data Index: 463730 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7739. Min Act: -0.0001

Data Index: 590828 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.6604. Min Act: -0.0001

Data Index: 1357549 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1006223 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.3903. Min Range: -2.3903

Max Act: 1.5854. Min Act: -0.0000

Data Index: 269109 (C4 (Web Text))

Max Activating Token Index: 431