Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5662. Min Act: -0.0001

Data Index: 1638702 (Python Code)

Max Activating Token Index: 347

Text #1

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1492992 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1513673 (Python Code)

Max Activating Token Index: 659

Text #3

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1551556 (Python Code)

Max Activating Token Index: 407

Text #4

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1402400 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1595279 (Python Code)

Max Activating Token Index: 416

Text #6

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1653592 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1416921 (Python Code)

Max Activating Token Index: 826

Text #8

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1641628 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4036. Min Act: -0.0001

Data Index: 1409762 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1525413 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3735. Min Act: -0.0001

Data Index: 1509068 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3709. Min Act: -0.0001

Data Index: 1516818 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1475170 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1452384 (Python Code)

Max Activating Token Index: 705

Text #15

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3750. Min Act: -0.0001

Data Index: 1547170 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1599495 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3529. Min Act: -0.0001

Data Index: 1530867 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1631062 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3536. Min Act: -0.0001

Data Index: 1458604 (Python Code)

Max Activating Token Index: 237