Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.5634. Min Act: -0.0001

Data Index: 47855 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.5196. Min Act: -0.0001

Data Index: 1601855 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.3611. Min Act: -0.0000

Data Index: 96418 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1574972 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0504. Min Act: -0.0001

Data Index: 1130779 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0060. Min Act: -0.0000

Data Index: 405954 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1370235 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9707. Min Act: -0.0001

Data Index: 618469 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.5634. Min Range: -1.5634

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1421560 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1393213 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9808. Min Act: -0.0000

Data Index: 449556 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9613. Min Act: -0.0000

Data Index: 120285 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9562. Min Act: -0.0000

Data Index: 160048 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8501. Min Act: -0.0001

Data Index: 417693 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8819. Min Act: -0.0001

Data Index: 1397869 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8751. Min Act: -0.0000

Data Index: 620115 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1343747 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8981. Min Act: -0.0001

Data Index: 1491633 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.9205. Min Act: -0.0001

Data Index: 1283885 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.5634. Min Range: -1.5634

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1600036 (Python Code)

Max Activating Token Index: 561