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

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

Neuron 5099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.9211. Min Act: 0.0000

Data Index: 776372 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.9052. Min Act: -0.0000

Data Index: 475928 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.8560. Min Act: -0.0000

Data Index: 122871 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.8601. Min Act: 0.0001

Data Index: 401903 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1188065 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7953. Min Act: -0.0000

Data Index: 236759 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.6935. Min Act: 0.0001

Data Index: 680018 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7689. Min Act: -0.0000

Data Index: 197277 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7456. Min Act: 0.0001

Data Index: 599070 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7115. Min Act: -0.0000

Data Index: 218018 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7053. Min Act: -0.0000

Data Index: 923101 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7021. Min Act: -0.0000

Data Index: 282358 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1149060 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1009765 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7665. Min Act: -0.0000

Data Index: 990575 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1228218 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7004. Min Act: -0.0000

Data Index: 977402 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.6948. Min Act: 0.0001

Data Index: 717060 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.7554. Min Act: -0.0000

Data Index: 519862 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.9211. Min Range: -0.9211

Max Act: 0.6612. Min Act: 0.0001

Data Index: 735308 (C4 (Web Text))

Max Activating Token Index: 19