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

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

Neuron 633 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: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1363653 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1368172 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0442. Min Act: -0.0005

Data Index: 1625168 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1509156 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0414. Min Act: -0.0005

Data Index: 1418738 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1421867 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0423. Min Act: -0.0005

Data Index: 1364187 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0422. Min Act: -0.0005

Data Index: 1554419 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0427. Min Act: -0.0005

Data Index: 1521801 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0404. Min Act: -0.0005

Data Index: 1387406 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1440044 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1544203 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1543996 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1624635 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1584998 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0416. Min Act: -0.0005

Data Index: 1564156 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0416. Min Act: -0.0005

Data Index: 1566483 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1469977 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1442935 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1638400 (Python Code)

Max Activating Token Index: 31