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

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

Neuron 1763 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7008. Min Range: -6.7008

Max Act: 6.7008. Min Act: -0.0000

Data Index: 1289667 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 6.7008. Min Range: -6.7008

Max Act: 6.1558. Min Act: -0.0000

Data Index: 130944 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 6.7008. Min Range: -6.7008

Max Act: 5.1728. Min Act: -0.0000

Data Index: 466671 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 6.7008. Min Range: -6.7008

Max Act: 4.2003. Min Act: -0.0000

Data Index: 138256 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 6.7008. Min Range: -6.7008

Max Act: 4.2341. Min Act: -0.0000

Data Index: 305514 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 6.7008. Min Range: -6.7008

Max Act: 4.0878. Min Act: -0.0000

Data Index: 622581 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 6.7008. Min Range: -6.7008

Max Act: 4.1498. Min Act: -0.0000

Data Index: 747101 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.9728. Min Act: -0.0000

Data Index: 406449 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.5796. Min Act: -0.0000

Data Index: 546718 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.0054. Min Act: -0.0000

Data Index: 356357 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.8461. Min Act: -0.0000

Data Index: 766858 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.5870. Min Act: -0.0000

Data Index: 852650 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.3096. Min Act: -0.0000

Data Index: 1308442 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.0241. Min Act: -0.0000

Data Index: 673397 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.1756. Min Act: -0.0000

Data Index: 561070 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 6.7008. Min Range: -6.7008

Max Act: 3.0118. Min Act: -0.0000

Data Index: 923891 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.3385. Min Act: -0.0000

Data Index: 343744 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.8066. Min Act: -0.0000

Data Index: 568602 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.4167. Min Act: -0.0000

Data Index: 990723 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 6.7008. Min Range: -6.7008

Max Act: 2.8931. Min Act: -0.0000

Data Index: 478553 (C4 (Web Text))

Max Activating Token Index: 646