Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4311 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3400. Min Range: -1.3400

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1393111 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 1.3400. Min Range: -1.3400

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1605827 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 1.3400. Min Range: -1.3400

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1560626 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.8598. Min Act: -0.0000

Data Index: 279299 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1159322 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.8049. Min Act: -0.0000

Data Index: 199905 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1104308 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1433515 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1617555 (Python Code)

Max Activating Token Index: 1004

Text #9

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1649889 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1041593 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7849. Min Act: -0.0000

Data Index: 244874 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7011. Min Act: -0.0000

Data Index: 844775 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.7105. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1361314 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.6814. Min Act: -0.0000

Data Index: 700664 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1635847 (Python Code)

Max Activating Token Index: 717

Text #18

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1369623 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 1.3400. Min Range: -1.3400

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1594136 (Python Code)

Max Activating Token Index: 539