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

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

Neuron 4791 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: 0.6210. Min Range: -0.6210

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1082047 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1540417 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.6059. Min Act: -0.0000

Data Index: 430237 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1604259 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5621. Min Act: -0.0000

Data Index: 852444 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1449405 (Python Code)

Max Activating Token Index: 837

Text #6

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1267052 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1360008 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5149. Min Act: -0.0000

Data Index: 55227 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1383269 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4516. Min Act: -0.0000

Data Index: 102716 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4347. Min Act: -0.0000

Data Index: 9726 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4454. Min Act: -0.0000

Data Index: 212969 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4402. Min Act: -0.0000

Data Index: 94729 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1034197 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1149469 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1585804 (Python Code)

Max Activating Token Index: 248

Text #17

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4365. Min Act: -0.0000

Data Index: 485988 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1463464 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1188903 (C4 (Web Text))

Max Activating Token Index: 458