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

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

Neuron 1144 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: 0.0542. Min Range: -0.0542

Max Act: 0.0533. Min Act: -0.0005

Data Index: 1507624 (Python Code)

Max Activating Token Index: 979

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0005

Data Index: 1375659 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0500. Min Act: -0.0005

Data Index: 1433758 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0475. Min Act: -0.0005

Data Index: 1608003 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1421437 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0524. Min Act: -0.0005

Data Index: 1555896 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0529. Min Act: -0.0005

Data Index: 1372010 (Python Code)

Max Activating Token Index: 282

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0505. Min Act: -0.0005

Data Index: 1639944 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0474. Min Act: -0.0005

Data Index: 1568460 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0476. Min Act: -0.0005

Data Index: 1653837 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0510. Min Act: -0.0005

Data Index: 1397405 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0497. Min Act: -0.0005

Data Index: 1563295 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0470. Min Act: -0.0005

Data Index: 1514122 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0488. Min Act: -0.0005

Data Index: 1606991 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0494. Min Act: -0.0005

Data Index: 931777 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1655000 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0461. Min Act: -0.0005

Data Index: 1442526 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0470. Min Act: -0.0005

Data Index: 1368033 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0502. Min Act: -0.0005

Data Index: 1626780 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0446. Min Act: -0.0005

Data Index: 1367836 (Python Code)

Max Activating Token Index: 67