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

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

Neuron 5831 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.9686. Min Act: -0.0002

Data Index: 23846 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.9594. Min Act: -0.0002

Data Index: 1538794 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.9449. Min Act: -0.0002

Data Index: 1341333 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8921. Min Act: -0.0002

Data Index: 1103207 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8938. Min Act: -0.0002

Data Index: 508623 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8987. Min Act: -0.0002

Data Index: 845538 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8892. Min Act: -0.0002

Data Index: 621416 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8880. Min Act: -0.0002

Data Index: 1564873 (Python Code)

Max Activating Token Index: 619

Text #8

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8973. Min Act: -0.0002

Data Index: 934559 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8710. Min Act: -0.0002

Data Index: 1339670 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8716. Min Act: -0.0002

Data Index: 915533 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8738. Min Act: -0.0002

Data Index: 308781 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8458. Min Act: -0.0002

Data Index: 50391 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8673. Min Act: -0.0002

Data Index: 1158589 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8508. Min Act: -0.0002

Data Index: 1174075 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8469. Min Act: -0.0002

Data Index: 278857 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8393. Min Act: -0.0002

Data Index: 1296629 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8484. Min Act: -0.0002

Data Index: 70921 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8375. Min Act: -0.0002

Data Index: 927668 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.9686. Min Range: -0.9686

Max Act: 0.8530. Min Act: -0.0002

Data Index: 258849 (C4 (Web Text))

Max Activating Token Index: 833