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

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

Neuron 3719 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.8868. Min Act: -0.0000

Data Index: 874456 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1331268 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.6518. Min Act: -0.0000

Data Index: 192266 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.6650. Min Act: 0.0000

Data Index: 922809 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5935. Min Act: -0.0000

Data Index: 206063 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5959. Min Act: -0.0000

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5668. Min Act: -0.0000

Data Index: 81104 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5440. Min Act: -0.0000

Data Index: 651970 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5779. Min Act: 0.0000

Data Index: 1133952 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5414. Min Act: -0.0000

Data Index: 859157 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5336. Min Act: -0.0000

Data Index: 576554 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1273078 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5393. Min Act: 0.0000

Data Index: 624231 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5354. Min Act: -0.0000

Data Index: 834141 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5353. Min Act: -0.0000

Data Index: 678719 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5120. Min Act: -0.0000

Data Index: 259732 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5129. Min Act: -0.0000

Data Index: 334874 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5531. Min Act: -0.0000

Data Index: 214831 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5215. Min Act: -0.0000

Data Index: 978392 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.8868. Min Range: -0.8868

Max Act: 0.5331. Min Act: -0.0000

Data Index: 283236 (C4 (Web Text))

Max Activating Token Index: 214