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

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

Neuron 1528 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: 0.9107. Min Range: -0.9107

Max Act: 0.9107. Min Act: -0.0000

Data Index: 711468 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7046. Min Act: -0.0000

Data Index: 939653 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1071207 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1107722 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1577646 (Python Code)

Max Activating Token Index: 652

Text #5

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6357. Min Act: -0.0000

Data Index: 929927 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6328. Min Act: -0.0000

Data Index: 472326 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1196738 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6645. Min Act: -0.0000

Data Index: 910915 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6698. Min Act: -0.0000

Data Index: 681735 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6415. Min Act: -0.0001

Data Index: 1534772 (Python Code)

Max Activating Token Index: 471

Text #11

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6345. Min Act: -0.0000

Data Index: 698081 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1410756 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1434872 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1525935 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1418610 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.5944. Min Act: -0.0000

Data Index: 560948 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6094. Min Act: -0.0000

Data Index: 800593 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1473531 (Python Code)

Max Activating Token Index: 712

Text #19

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.5826. Min Act: -0.0000

Data Index: 752134 (C4 (Web Text))

Max Activating Token Index: 893