Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 258 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3696. Min Act: -0.0005

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2633. Min Act: -0.0005

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2276. Min Act: -0.0005

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1973. Min Act: -0.0005

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1811. Min Act: -0.0005

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1298. Min Act: -0.0005

Data Index: 234425 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1182. Min Act: -0.0005

Data Index: 542144 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0871. Min Act: -0.0005

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0690. Min Act: -0.0005

Data Index: 790305 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0687. Min Act: -0.0005

Data Index: 700231 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0653. Min Act: -0.0005

Data Index: 363700 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0475. Min Act: -0.0005

Data Index: 51849 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0455. Min Act: -0.0005

Data Index: 642506 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0475. Min Act: -0.0005

Data Index: 485449 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0347. Min Act: -0.0005

Data Index: 847261 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1066676 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0399. Min Act: -0.0005

Data Index: 519414 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1202130 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1193334 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.0320. Min Act: -0.0005

Data Index: 389796 (C4 (Web Text))

Max Activating Token Index: 574