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

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

Neuron 409 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0006

Data Index: 726655 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1333233 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0433. Min Act: -0.0006

Data Index: 680607 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0407. Min Act: -0.0006

Data Index: 312667 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0432. Min Act: -0.0006

Data Index: 370625 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0404. Min Act: -0.0006

Data Index: 36149 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0438. Min Act: -0.0006

Data Index: 288278 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0435. Min Act: -0.0006

Data Index: 274845 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0425. Min Act: -0.0006

Data Index: 652360 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0407. Min Act: -0.0006

Data Index: 702450 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0390. Min Act: -0.0006

Data Index: 970233 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0424. Min Act: -0.0006

Data Index: 1350652 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1328378 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0415. Min Act: -0.0006

Data Index: 704089 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0372. Min Act: -0.0006

Data Index: 48382 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1141819 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0386. Min Act: -0.0006

Data Index: 105651 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1200098 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0396. Min Act: -0.0006

Data Index: 624177 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1132614 (C4 (Web Text))

Max Activating Token Index: 165