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

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

Neuron 2171 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0814. Min Act: -0.0001

Data Index: 475068 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1000212 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0932. Min Act: -0.0001

Data Index: 466851 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9772. Min Act: -0.0001

Data Index: 1002759 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0896. Min Act: -0.0001

Data Index: 1637842 (Python Code)

Max Activating Token Index: 873

Text #5

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0927. Min Act: -0.0001

Data Index: 1336875 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0242. Min Act: -0.0001

Data Index: 1584341 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0165. Min Act: -0.0001

Data Index: 711352 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9848. Min Act: -0.0001

Data Index: 882342 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9154. Min Act: -0.0001

Data Index: 1403597 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9706. Min Act: -0.0001

Data Index: 541807 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9737. Min Act: -0.0001

Data Index: 329617 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9388. Min Act: -0.0001

Data Index: 1129168 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1456257 (Python Code)

Max Activating Token Index: 131

Text #14

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9370. Min Act: -0.0001

Data Index: 389976 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9637. Min Act: -0.0001

Data Index: 1070590 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9290. Min Act: -0.0001

Data Index: 246148 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9825. Min Act: -0.0001

Data Index: 1465934 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9480. Min Act: -0.0001

Data Index: 827584 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9724. Min Act: -0.0001

Data Index: 327573 (C4 (Web Text))

Max Activating Token Index: 818