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

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

Neuron 5905 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.8200. Min Act: -0.0000

Data Index: 926199 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.7806. Min Act: -0.0000

Data Index: 720866 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6561. Min Act: -0.0000

Data Index: 510995 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.6058. Min Act: -0.0000

Data Index: 27124 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3952. Min Act: -0.0000

Data Index: 820881 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1207938 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.4104. Min Act: -0.0000

Data Index: 775195 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3186. Min Act: -0.0000

Data Index: 138532 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3892. Min Act: -0.0000

Data Index: 293016 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.4742. Min Act: -0.0000

Data Index: 388873 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3617. Min Act: -0.0000

Data Index: 5067 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1097981 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3267. Min Act: -0.0000

Data Index: 176286 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.2648. Min Act: -0.0000

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3187. Min Act: -0.0000

Data Index: 304186 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1048704 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3030. Min Act: -0.0000

Data Index: 574434 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.2982. Min Act: -0.0000

Data Index: 730110 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.3539. Min Act: -0.0000

Data Index: 336214 (C4 (Web Text))

Max Activating Token Index: 342