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

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

Neuron 3489 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: 4.3673. Min Range: -4.3673

Max Act: 4.3673. Min Act: -0.0000

Data Index: 337933 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.6867. Min Act: -0.0000

Data Index: 1205916 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.6287. Min Act: -0.0000

Data Index: 715727 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.1133. Min Act: -0.0000

Data Index: 963539 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.3013. Min Act: -0.0000

Data Index: 415237 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.2266. Min Act: -0.0000

Data Index: 321678 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.5512. Min Act: -0.0000

Data Index: 811862 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.2121. Min Act: -0.0000

Data Index: 1124825 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.1442. Min Act: -0.0000

Data Index: 712349 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.1272. Min Act: -0.0000

Data Index: 165912 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.1079. Min Act: -0.0000

Data Index: 1349795 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.0126. Min Act: -0.0000

Data Index: 993829 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 4.3673. Min Range: -4.3673

Max Act: 2.9874. Min Act: -0.0000

Data Index: 59010 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.0079. Min Act: -0.0000

Data Index: 358137 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 4.3673. Min Range: -4.3673

Max Act: 2.8184. Min Act: -0.0000

Data Index: 881200 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.2784. Min Act: -0.0000

Data Index: 346277 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 4.3673. Min Range: -4.3673

Max Act: 2.9491. Min Act: -0.0000

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 4.3673. Min Range: -4.3673

Max Act: 2.8969. Min Act: -0.0000

Data Index: 50393 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 4.3673. Min Range: -4.3673

Max Act: 3.0199. Min Act: -0.0000

Data Index: 1039696 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 4.3673. Min Range: -4.3673

Max Act: 2.8708. Min Act: -0.0000

Data Index: 526910 (C4 (Web Text))

Max Activating Token Index: 1007