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

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

Neuron 4784 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: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1064323 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0552. Min Act: -0.0003

Data Index: 336723 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0523. Min Act: -0.0003

Data Index: 809405 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0474. Min Act: -0.0002

Data Index: 49435 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0435. Min Act: -0.0003

Data Index: 747592 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0432. Min Act: -0.0003

Data Index: 924414 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0431. Min Act: -0.0003

Data Index: 202648 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1059672 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0413. Min Act: -0.0003

Data Index: 484650 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1122264 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0378. Min Act: -0.0003

Data Index: 373132 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0383. Min Act: -0.0003

Data Index: 588571 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0390. Min Act: -0.0003

Data Index: 215027 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0389. Min Act: -0.0003

Data Index: 568942 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1190242 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1201328 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1316574 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0361. Min Act: -0.0003

Data Index: 388495 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1448595 (Python Code)

Max Activating Token Index: 659