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

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

Neuron 1448 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4583. Min Act: -0.0000

Data Index: 212466 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4746. Min Act: -0.0000

Data Index: 933782 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1122518 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1351895 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3917. Min Act: -0.0000

Data Index: 395366 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3803. Min Act: -0.0000

Data Index: 557134 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3993. Min Act: -0.0000

Data Index: 152115 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3671. Min Act: -0.0000

Data Index: 64502 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3750. Min Act: -0.0000

Data Index: 710343 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3558. Min Act: -0.0000

Data Index: 409913 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1066381 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3306. Min Act: -0.0000

Data Index: 332865 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1245616 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1014397 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3598. Min Act: -0.0000

Data Index: 380929 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3487. Min Act: -0.0000

Data Index: 476262 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1019483 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3294. Min Act: -0.0000

Data Index: 195277 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3747. Min Act: -0.0000

Data Index: 382209 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3307. Min Act: -0.0000

Data Index: 874886 (C4 (Web Text))

Max Activating Token Index: 135