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

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

Neuron 3815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2489. Min Act: -0.0000

Data Index: 675152 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2465. Min Act: -0.0000

Data Index: 887662 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2560. Min Act: -0.0000

Data Index: 346582 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1113484 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2310. Min Act: -0.0000

Data Index: 60572 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2479. Min Act: -0.0000

Data Index: 859870 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2123. Min Act: -0.0000

Data Index: 306487 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1090126 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2008. Min Act: -0.0000

Data Index: 359012 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1108457 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1834. Min Act: -0.0000

Data Index: 571432 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1333319 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1592. Min Act: -0.0000

Data Index: 852536 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1639. Min Act: -0.0000

Data Index: 537799 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1669. Min Act: -0.0000

Data Index: 188145 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1117802 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1596. Min Act: -0.0000

Data Index: 286659 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1657. Min Act: -0.0000

Data Index: 530239 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1346953 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1080974 (C4 (Web Text))

Max Activating Token Index: 818