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

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

Neuron 521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.2008. Min Act: -0.0000

Data Index: 997989 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1055649 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1413. Min Act: -0.0000

Data Index: 414717 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1035211 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1538070 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1267. Min Act: -0.0000

Data Index: 240755 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1089. Min Act: -0.0000

Data Index: 505986 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.1033. Min Act: -0.0000

Data Index: 212947 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1622114 (Python Code)

Max Activating Token Index: 891

Text #9

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0848. Min Act: -0.0000

Data Index: 591794 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0843. Min Act: -0.0000

Data Index: 195325 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0807. Min Act: -0.0000

Data Index: 901609 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1649566 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1441559 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0725. Min Act: -0.0000

Data Index: 594051 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1000080 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1592930 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1537476 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1366865 (Python Code)

Max Activating Token Index: 930

Text #19

Max Range: 0.2008. Min Range: -0.2008

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1410343 (Python Code)

Max Activating Token Index: 466