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

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

Neuron 3539 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0205. Min Range: -1.0205

Max Act: 1.0205. Min Act: -0.0002

Data Index: 824129 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.0205. Min Range: -1.0205

Max Act: 1.0138. Min Act: -0.0002

Data Index: 684249 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8312. Min Act: -0.0002

Data Index: 553369 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8555. Min Act: -0.0002

Data Index: 917055 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8051. Min Act: -0.0002

Data Index: 954319 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7962. Min Act: -0.0002

Data Index: 1315269 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7665. Min Act: -0.0002

Data Index: 244759 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.8120. Min Act: -0.0002

Data Index: 1213292 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6534. Min Act: -0.0002

Data Index: 639388 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7760. Min Act: -0.0002

Data Index: 1304652 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6888. Min Act: -0.0002

Data Index: 352681 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6842. Min Act: -0.0002

Data Index: 76428 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7223. Min Act: -0.0002

Data Index: 507632 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6825. Min Act: -0.0002

Data Index: 1109914 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7098. Min Act: -0.0002

Data Index: 434541 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7108. Min Act: -0.0002

Data Index: 837919 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6991. Min Act: -0.0002

Data Index: 279108 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.6521. Min Act: -0.0002

Data Index: 27962 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7052. Min Act: -0.0002

Data Index: 598571 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.0205. Min Range: -1.0205

Max Act: 0.7445. Min Act: -0.0002

Data Index: 1346377 (C4 (Web Text))

Max Activating Token Index: 344