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

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

Neuron 3032 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: 4.8550. Min Range: -4.8550

Max Act: 4.8550. Min Act: -0.0000

Data Index: 59175 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 4.8550. Min Range: -4.8550

Max Act: 3.2061. Min Act: -0.0000

Data Index: 709959 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 4.8550. Min Range: -4.8550

Max Act: 3.0751. Min Act: -0.0000

Data Index: 193479 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.8954. Min Act: -0.0000

Data Index: 1229754 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.6840. Min Act: -0.0000

Data Index: 677441 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.7774. Min Act: -0.0000

Data Index: 873584 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.7111. Min Act: -0.0000

Data Index: 465939 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.6655. Min Act: -0.0000

Data Index: 619415 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.6540. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.6299. Min Act: -0.0000

Data Index: 1046393 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.6024. Min Act: -0.0000

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.4388. Min Act: -0.0000

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.4253. Min Act: -0.0000

Data Index: 1010741 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.4155. Min Act: -0.0000

Data Index: 633168 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.3861. Min Act: -0.0000

Data Index: 744892 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.3732. Min Act: -0.0000

Data Index: 986146 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.3119. Min Act: -0.0000

Data Index: 7093 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.2172. Min Act: -0.0000

Data Index: 64087 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.1896. Min Act: -0.0000

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 4.8550. Min Range: -4.8550

Max Act: 2.1798. Min Act: -0.0000

Data Index: 208071 (C4 (Web Text))

Max Activating Token Index: 746