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

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

Neuron 3954 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: 0.9840. Min Range: -0.9840

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1551022 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.9731. Min Act: -0.0001

Data Index: 750829 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.9517. Min Act: -0.0001

Data Index: 394053 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1443146 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1381830 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8334. Min Act: -0.0001

Data Index: 1453685 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1389971 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1628947 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8845. Min Act: -0.0001

Data Index: 680509 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1531571 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1483159 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8266. Min Act: -0.0001

Data Index: 933674 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8193. Min Act: -0.0001

Data Index: 249549 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8759. Min Act: -0.0001

Data Index: 219657 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8215. Min Act: -0.0001

Data Index: 279489 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8079. Min Act: -0.0001

Data Index: 1630175 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1069057 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7320. Min Act: -0.0001

Data Index: 88404 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1453000 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.8016. Min Act: -0.0001

Data Index: 590886 (C4 (Web Text))

Max Activating Token Index: 274