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

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

Neuron 1764 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1430356 (Python Code)

Max Activating Token Index: 268

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1501090 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1458726 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1562313 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1475274 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1441054 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1617714 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1458811 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1569257 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1381649 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1591643 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1648574 (Python Code)

Max Activating Token Index: 585

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1375497 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1442059 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1635110 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1463298 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1531900 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1452386 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1607904 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: 0.0000

Data Index: 1361489 (Python Code)

Max Activating Token Index: 607