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

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

Neuron 3646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.6779. Min Act: -0.0000

Data Index: 412860 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.6568. Min Act: -0.0000

Data Index: 720446 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.5603. Min Act: -0.0000

Data Index: 735093 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.6427. Min Act: -0.0000

Data Index: 388833 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.5377. Min Act: 0.0000

Data Index: 1182413 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.6186. Min Act: -0.0000

Data Index: 817689 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1050790 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4864. Min Act: -0.0000

Data Index: 348475 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4059. Min Act: -0.0000

Data Index: 809462 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.5348. Min Act: -0.0000

Data Index: 732585 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.3879. Min Act: -0.0000

Data Index: 417150 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1091011 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4786. Min Act: -0.0000

Data Index: 818133 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4613. Min Act: -0.0000

Data Index: 443492 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.2752. Min Act: -0.0000

Data Index: 298768 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1429811 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.4344. Min Act: -0.0000

Data Index: 1025667 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.3475. Min Act: -0.0000

Data Index: 419569 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1022624 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.6779. Min Range: -1.6779

Max Act: 1.3235. Min Act: -0.0000

Data Index: 312810 (C4 (Web Text))

Max Activating Token Index: 228