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

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

Neuron 3863 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.8911. Min Act: -0.0000

Data Index: 955811 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.7794. Min Act: -0.0000

Data Index: 611003 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.7360. Min Act: -0.0000

Data Index: 721951 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.6786. Min Act: -0.0000

Data Index: 446572 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.7249. Min Act: -0.0000

Data Index: 606828 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.6230. Min Act: -0.0000

Data Index: 1062723 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.6809. Min Act: -0.0000

Data Index: 17642 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.5563. Min Act: -0.0000

Data Index: 95260 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.6261. Min Act: -0.0000

Data Index: 424692 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.6061. Min Act: -0.0000

Data Index: 432439 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.4878. Min Act: -0.0000

Data Index: 304659 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.5520. Min Act: -0.0000

Data Index: 523626 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2840. Min Act: -0.0000

Data Index: 379577 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1118888 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.1902. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2404. Min Act: -0.0000

Data Index: 165256 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1282585 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1277051 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.3174. Min Act: -0.0000

Data Index: 115716 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1138951 (C4 (Web Text))

Max Activating Token Index: 211