Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2033 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1840. Min Range: -1.1840

Max Act: 1.1840. Min Act: -0.0001

Data Index: 745812 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.1840. Min Range: -1.1840

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1010007 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9709. Min Act: -0.0001

Data Index: 294955 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9602. Min Act: -0.0001

Data Index: 1005057 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9528. Min Act: -0.0001

Data Index: 431248 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8033. Min Act: -0.0001

Data Index: 552181 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9387. Min Act: -0.0001

Data Index: 1383187 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8449. Min Act: -0.0001

Data Index: 1116921 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9012. Min Act: -0.0001

Data Index: 932011 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1372490 (Python Code)

Max Activating Token Index: 516

Text #10

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1465203 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8806. Min Act: -0.0001

Data Index: 288552 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8479. Min Act: -0.0001

Data Index: 1597512 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8594. Min Act: -0.0001

Data Index: 530832 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8050. Min Act: -0.0001

Data Index: 943746 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.9067. Min Act: -0.0001

Data Index: 1136065 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8402. Min Act: -0.0001

Data Index: 492703 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1446992 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.8671. Min Act: -0.0001

Data Index: 1591719 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.1840. Min Range: -1.1840

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1214117 (C4 (Web Text))

Max Activating Token Index: 547