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

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

Neuron 28 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8448. Min Act: -0.0000

Data Index: 468552 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7757. Min Act: -0.0000

Data Index: 403293 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1120018 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1109070 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8019. Min Act: -0.0000

Data Index: 653321 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7267. Min Act: -0.0000

Data Index: 137260 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7411. Min Act: -0.0000

Data Index: 549519 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7452. Min Act: -0.0000

Data Index: 368197 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6957. Min Act: -0.0000

Data Index: 699024 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6718. Min Act: -0.0000

Data Index: 112018 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6843. Min Act: -0.0000

Data Index: 981355 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6692. Min Act: -0.0000

Data Index: 407234 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6740. Min Act: -0.0000

Data Index: 471586 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1248994 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1321975 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6365. Min Act: -0.0000

Data Index: 460685 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1154222 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1303871 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7085. Min Act: -0.0000

Data Index: 524777 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6570. Min Act: -0.0000

Data Index: 805282 (C4 (Web Text))

Max Activating Token Index: 412