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

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

Neuron 1067 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0003

Data Index: 289238 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0478. Min Act: -0.0003

Data Index: 653868 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0481. Min Act: -0.0003

Data Index: 299815 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0454. Min Act: -0.0003

Data Index: 416203 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0419. Min Act: -0.0003

Data Index: 52590 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1052291 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1216451 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1232209 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0404. Min Act: -0.0003

Data Index: 356348 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0384. Min Act: -0.0002

Data Index: 842715 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0373. Min Act: -0.0003

Data Index: 780905 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0361. Min Act: -0.0003

Data Index: 751481 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0380. Min Act: -0.0003

Data Index: 759870 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0363. Min Act: -0.0003

Data Index: 220160 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1064026 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1256934 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0353. Min Act: -0.0003

Data Index: 407937 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0363. Min Act: -0.0003

Data Index: 301614 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0356. Min Act: -0.0003

Data Index: 603803 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0347. Min Act: -0.0003

Data Index: 389794 (C4 (Web Text))

Max Activating Token Index: 131