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

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

Neuron 1047 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: 0.7941. Min Range: -0.7941

Max Act: 0.7941. Min Act: -0.0000

Data Index: 871567 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6744. Min Act: -0.0000

Data Index: 402020 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6655. Min Act: -0.0000

Data Index: 621946 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7122. Min Act: -0.0000

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6998. Min Act: -0.0000

Data Index: 847029 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6691. Min Act: -0.0000

Data Index: 491711 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6242. Min Act: -0.0000

Data Index: 441839 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5886. Min Act: -0.0000

Data Index: 232902 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6170. Min Act: -0.0000

Data Index: 197261 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5768. Min Act: -0.0000

Data Index: 947738 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1148696 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1190098 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1357205 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1251449 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5440. Min Act: -0.0000

Data Index: 85536 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5096. Min Act: -0.0000

Data Index: 141570 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4948. Min Act: -0.0000

Data Index: 160822 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5229. Min Act: -0.0000

Data Index: 806541 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5392. Min Act: -0.0000

Data Index: 440992 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5389. Min Act: -0.0000

Data Index: 872913 (C4 (Web Text))

Max Activating Token Index: 438