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

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

Neuron 3129 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.5698. Min Act: -0.0000

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.4884. Min Act: -0.0000

Data Index: 830643 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.4433. Min Act: -0.0000

Data Index: 561418 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.3096. Min Act: -0.0000

Data Index: 956705 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1270293 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.1803. Min Act: -0.0000

Data Index: 58383 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.1950. Min Act: -0.0000

Data Index: 208812 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.1633. Min Act: -0.0000

Data Index: 1388723 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.1228. Min Act: -0.0000

Data Index: 355321 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.0700. Min Act: -0.0000

Data Index: 339986 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.0743. Min Act: -0.0000

Data Index: 1172967 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.0522. Min Act: -0.0000

Data Index: 971420 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.0037. Min Act: -0.0000

Data Index: 644103 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.2023. Min Act: -0.0000

Data Index: 250709 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 2.5698. Min Range: -2.5698

Max Act: 1.8710. Min Act: -0.0000

Data Index: 1310904 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 2.5698. Min Range: -2.5698

Max Act: 1.8483. Min Act: -0.0000

Data Index: 852916 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 2.5698. Min Range: -2.5698

Max Act: 1.9490. Min Act: -0.0000

Data Index: 842752 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 2.5698. Min Range: -2.5698

Max Act: 2.0194. Min Act: -0.0000

Data Index: 1069575 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 2.5698. Min Range: -2.5698

Max Act: 1.9872. Min Act: -0.0000

Data Index: 1073207 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 2.5698. Min Range: -2.5698

Max Act: 1.8691. Min Act: -0.0000

Data Index: 38832 (C4 (Web Text))

Max Activating Token Index: 928