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

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

Neuron 1760 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: 1.9310. Min Range: -1.9310

Max Act: 1.8540. Min Act: -0.0000

Data Index: 689792 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.8337. Min Act: -0.0000

Data Index: 771089 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.9310. Min Act: -0.0000

Data Index: 955291 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1112485 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.5417. Min Act: -0.0000

Data Index: 642999 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.6062. Min Act: -0.0000

Data Index: 101392 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.6931. Min Act: -0.0000

Data Index: 250372 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.5973. Min Act: -0.0000

Data Index: 532548 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.5823. Min Act: -0.0000

Data Index: 37131 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.6553. Min Act: -0.0000

Data Index: 434438 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.5585. Min Act: -0.0000

Data Index: 18403 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.4547. Min Act: -0.0000

Data Index: 632134 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.5107. Min Act: -0.0000

Data Index: 226912 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.4862. Min Act: -0.0000

Data Index: 347974 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.3948. Min Act: -0.0000

Data Index: 565700 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.3774. Min Act: -0.0000

Data Index: 798196 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.6204. Min Act: -0.0000

Data Index: 799023 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.4366. Min Act: -0.0000

Data Index: 801254 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1054796 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.9310. Min Range: -1.9310

Max Act: 1.3533. Min Act: -0.0000

Data Index: 264007 (C4 (Web Text))

Max Activating Token Index: 580