Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3420 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1357536 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1974. Min Act: -0.0000

Data Index: 807424 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1119970 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1648. Min Act: -0.0000

Data Index: 797772 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1668. Min Act: -0.0000

Data Index: 601052 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1320187 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1306322 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1557. Min Act: -0.0000

Data Index: 326254 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1601. Min Act: -0.0000

Data Index: 785433 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1546. Min Act: -0.0000

Data Index: 339284 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1589. Min Act: -0.0000

Data Index: 328068 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1122377 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1556. Min Act: -0.0000

Data Index: 491660 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1532. Min Act: -0.0000

Data Index: 864177 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1541. Min Act: -0.0000

Data Index: 777264 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1199000 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1515. Min Act: -0.0000

Data Index: 761086 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1460. Min Act: -0.0000

Data Index: 604940 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1520. Min Act: -0.0000

Data Index: 276048 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2011. Min Range: -0.2011

Max Act: 0.1516. Min Act: -0.0000

Data Index: 968160 (C4 (Web Text))

Max Activating Token Index: 5