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

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

Neuron 2689 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.7925. Min Act: -0.0002

Data Index: 1073553 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.6289. Min Act: -0.0002

Data Index: 529118 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5790. Min Act: -0.0002

Data Index: 1170498 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5546. Min Act: -0.0002

Data Index: 830746 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5709. Min Act: -0.0002

Data Index: 479461 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5077. Min Act: -0.0002

Data Index: 217990 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4039. Min Act: -0.0002

Data Index: 176379 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3328. Min Act: -0.0002

Data Index: 765542 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3556. Min Act: -0.0002

Data Index: 1017891 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3579. Min Act: -0.0002

Data Index: 252163 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3037. Min Act: -0.0002

Data Index: 404844 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2434. Min Act: -0.0002

Data Index: 47769 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3111. Min Act: -0.0002

Data Index: 100745 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2753. Min Act: -0.0002

Data Index: 106576 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2705. Min Act: -0.0002

Data Index: 508430 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2612. Min Act: -0.0002

Data Index: 668343 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2167. Min Act: -0.0002

Data Index: 756382 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3294. Min Act: -0.0002

Data Index: 802998 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2222. Min Act: -0.0002

Data Index: 252066 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.1807. Min Act: -0.0002

Data Index: 60986 (C4 (Web Text))

Max Activating Token Index: 734