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

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

Neuron 979 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1420563 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0708. Min Act: -0.0000

Data Index: 131428 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1425496 (Python Code)

Max Activating Token Index: 487

Text #3

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0203. Min Act: -0.0000

Data Index: 514076 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1304007 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1028880 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1484775 (Python Code)

Max Activating Token Index: 820

Text #7

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9535. Min Act: -0.0000

Data Index: 16961 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9419. Min Act: -0.0000

Data Index: 610910 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1512476 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8959. Min Act: -0.0000

Data Index: 478508 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8671. Min Act: -0.0000

Data Index: 922431 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8687. Min Act: -0.0000

Data Index: 173675 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1150182 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8687. Min Act: -0.0000

Data Index: 370647 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8225. Min Act: -0.0000

Data Index: 68579 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1018965 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1351701 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8003. Min Act: -0.0000

Data Index: 690909 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8026. Min Act: -0.0000

Data Index: 398861 (C4 (Web Text))

Max Activating Token Index: 517