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

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

Neuron 4331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1832. Min Range: -3.1832

Max Act: 3.1187. Min Act: -0.0000

Data Index: 611774 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 3.1832. Min Range: -3.1832

Max Act: 3.1832. Min Act: -0.0000

Data Index: 1033385 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 3.1832. Min Range: -3.1832

Max Act: 3.0586. Min Act: -0.0000

Data Index: 497776 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 3.1832. Min Range: -3.1832

Max Act: 3.0425. Min Act: -0.0000

Data Index: 127110 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.4722. Min Act: -0.0000

Data Index: 1347514 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.6012. Min Act: -0.0000

Data Index: 774666 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.1832. Min Range: -3.1832

Max Act: 3.0370. Min Act: -0.0000

Data Index: 552456 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.7552. Min Act: -0.0000

Data Index: 46525 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.6787. Min Act: -0.0000

Data Index: 1261327 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.1902. Min Act: -0.0000

Data Index: 447171 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.9247. Min Act: -0.0000

Data Index: 228135 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.3458. Min Act: -0.0000

Data Index: 347537 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.3530. Min Act: -0.0000

Data Index: 61417 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.4828. Min Act: -0.0000

Data Index: 970147 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.3498. Min Act: -0.0000

Data Index: 540049 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.2741. Min Act: -0.0000

Data Index: 1119291 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.5141. Min Act: -0.0000

Data Index: 138645 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.3730. Min Act: -0.0000

Data Index: 814030 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.1978. Min Act: -0.0000

Data Index: 151229 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 3.1832. Min Range: -3.1832

Max Act: 2.5434. Min Act: -0.0000

Data Index: 1008781 (C4 (Web Text))

Max Activating Token Index: 781