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

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

Neuron 3725 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: 0.6724. Min Range: -0.6724

Max Act: 0.6724. Min Act: -0.0000

Data Index: 654328 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1007424 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5977. Min Act: -0.0000

Data Index: 805276 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.6110. Min Act: -0.0000

Data Index: 890866 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1337005 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5422. Min Act: -0.0000

Data Index: 160987 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1103489 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5210. Min Act: -0.0000

Data Index: 142974 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5347. Min Act: -0.0000

Data Index: 796862 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1107778 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5305. Min Act: -0.0000

Data Index: 135711 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5018. Min Act: -0.0000

Data Index: 198576 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5247. Min Act: -0.0000

Data Index: 216055 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5614. Min Act: -0.0000

Data Index: 423087 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5372. Min Act: -0.0000

Data Index: 412580 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4882. Min Act: -0.0000

Data Index: 574465 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4814. Min Act: -0.0000

Data Index: 365779 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5271. Min Act: -0.0000

Data Index: 965795 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1242627 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5017. Min Act: -0.0000

Data Index: 474401 (C4 (Web Text))

Max Activating Token Index: 991