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

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

Neuron 5975 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: 4.4013. Min Range: -4.4013

Max Act: 4.4013. Min Act: -0.0000

Data Index: 121762 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.5501. Min Act: -0.0000

Data Index: 1345007 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.5298. Min Act: -0.0000

Data Index: 931874 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.3406. Min Act: -0.0000

Data Index: 288978 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.2914. Min Act: -0.0000

Data Index: 760884 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.5835. Min Act: -0.0000

Data Index: 1319633 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.1951. Min Act: -0.0000

Data Index: 176530 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.3301. Min Act: -0.0000

Data Index: 945102 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.1767. Min Act: -0.0000

Data Index: 378434 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 4.4013. Min Range: -4.4013

Max Act: 3.2639. Min Act: -0.0000

Data Index: 220244 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.9896. Min Act: -0.0000

Data Index: 918662 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.9378. Min Act: -0.0000

Data Index: 381181 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.9735. Min Act: -0.0000

Data Index: 1190213 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.8625. Min Act: -0.0000

Data Index: 845360 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.7951. Min Act: -0.0000

Data Index: 358413 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.6847. Min Act: -0.0000

Data Index: 1012500 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.8212. Min Act: -0.0000

Data Index: 626156 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.9596. Min Act: -0.0000

Data Index: 1075771 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.7670. Min Act: -0.0000

Data Index: 1342942 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 4.4013. Min Range: -4.4013

Max Act: 2.3620. Min Act: -0.0000

Data Index: 1065849 (C4 (Web Text))

Max Activating Token Index: 823