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

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

Neuron 4838 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8517. Min Act: -0.0000

Data Index: 685092 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.8026. Min Act: -0.0000

Data Index: 206679 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7046. Min Act: 0.0001

Data Index: 1358405 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6466. Min Act: -0.0000

Data Index: 963462 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6303. Min Act: 0.0001

Data Index: 362003 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1000182 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6452. Min Act: 0.0000

Data Index: 843215 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1131212 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.5234. Min Act: 0.0000

Data Index: 1303886 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.5349. Min Act: -0.0000

Data Index: 26802 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4834. Min Act: 0.0001

Data Index: 546574 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4865. Min Act: -0.0000

Data Index: 733048 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1246759 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4754. Min Act: -0.0000

Data Index: 247905 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4901. Min Act: -0.0000

Data Index: 495952 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4424. Min Act: -0.0000

Data Index: 140264 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4710. Min Act: -0.0000

Data Index: 574758 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1133255 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4954. Min Act: -0.0000

Data Index: 644353 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4781. Min Act: 0.0000

Data Index: 32204 (C4 (Web Text))

Max Activating Token Index: 39