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

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

Neuron 3686 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5794. Min Act: -0.0000

Data Index: 33117 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5338. Min Act: -0.0000

Data Index: 642638 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1156990 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5435. Min Act: -0.0000

Data Index: 433792 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5474. Min Act: -0.0000

Data Index: 275664 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5502. Min Act: -0.0000

Data Index: 115068 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.5045. Min Act: -0.0000

Data Index: 147835 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.4199. Min Act: -0.0000

Data Index: 630904 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.4335. Min Act: -0.0000

Data Index: 729011 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3683. Min Act: -0.0000

Data Index: 563003 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3978. Min Act: -0.0000

Data Index: 567719 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3371. Min Act: -0.0000

Data Index: 278285 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3886. Min Act: -0.0000

Data Index: 129856 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3928. Min Act: -0.0000

Data Index: 681381 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1062179 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1246761 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3441. Min Act: -0.0000

Data Index: 250832 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3524. Min Act: -0.0000

Data Index: 485313 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3635. Min Act: -0.0000

Data Index: 400695 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.5794. Min Range: -0.5794

Max Act: 0.3453. Min Act: -0.0000

Data Index: 714845 (C4 (Web Text))

Max Activating Token Index: 778