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

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

Neuron 1770 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: 5.7016. Min Range: -5.7016

Max Act: 5.7016. Min Act: -0.0000

Data Index: 1145371 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 5.7016. Min Range: -5.7016

Max Act: 5.0897. Min Act: -0.0000

Data Index: 328280 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.8642. Min Act: -0.0000

Data Index: 930821 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.9173. Min Act: -0.0000

Data Index: 947381 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.7380. Min Act: -0.0000

Data Index: 902461 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.9065. Min Act: -0.0000

Data Index: 399011 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.5331. Min Act: -0.0000

Data Index: 1199091 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.3829. Min Act: -0.0000

Data Index: 274807 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.5385. Min Act: -0.0000

Data Index: 1352046 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.3751. Min Act: -0.0000

Data Index: 1124062 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.3130. Min Act: -0.0000

Data Index: 56766 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.4614. Min Act: -0.0000

Data Index: 811398 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.2637. Min Act: -0.0000

Data Index: 1277967 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.1808. Min Act: -0.0000

Data Index: 737930 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.0700. Min Act: -0.0000

Data Index: 543404 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.0853. Min Act: -0.0000

Data Index: 984459 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 5.7016. Min Range: -5.7016

Max Act: 3.8220. Min Act: -0.0000

Data Index: 731962 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 5.7016. Min Range: -5.7016

Max Act: 4.0130. Min Act: -0.0000

Data Index: 623844 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 5.7016. Min Range: -5.7016

Max Act: 3.8007. Min Act: -0.0000

Data Index: 955404 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.7016. Min Range: -5.7016

Max Act: 3.9414. Min Act: -0.0000

Data Index: 985991 (C4 (Web Text))

Max Activating Token Index: 769