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

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

Neuron 1467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.2080. Min Act: -0.0001

Data Index: 867780 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1862. Min Act: -0.0001

Data Index: 305987 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1770. Min Act: -0.0001

Data Index: 382269 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1898. Min Act: -0.0001

Data Index: 676394 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1110020 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1160466 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1330068 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1347024 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1056666 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1622. Min Act: -0.0001

Data Index: 118275 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1590. Min Act: -0.0001

Data Index: 578275 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1604. Min Act: -0.0001

Data Index: 117528 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1314. Min Act: -0.0001

Data Index: 176199 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1554. Min Act: -0.0001

Data Index: 461765 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1551. Min Act: -0.0001

Data Index: 180006 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1267252 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1052283 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1172644 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1509. Min Act: -0.0001

Data Index: 513592 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1409. Min Act: -0.0001

Data Index: 372088 (C4 (Web Text))

Max Activating Token Index: 706