Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1424437 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1175695 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1224. Min Act: -0.0001

Data Index: 643818 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1015. Min Act: -0.0001

Data Index: 751702 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1509794 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1040. Min Act: -0.0001

Data Index: 50609 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1104. Min Act: -0.0001

Data Index: 236991 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1029. Min Act: -0.0001

Data Index: 203296 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1170764 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1385838 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1465486 (Python Code)

Max Activating Token Index: 809

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0988. Min Act: -0.0001

Data Index: 154557 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1236. Min Act: -0.0001

Data Index: 70231 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1108. Min Act: -0.0001

Data Index: 882576 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1057. Min Act: -0.0001

Data Index: 818531 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1398698 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1004. Min Act: -0.0001

Data Index: 417677 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1610905 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1474227 (Python Code)

Max Activating Token Index: 579

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0982. Min Act: -0.0001

Data Index: 711877 (C4 (Web Text))

Max Activating Token Index: 524