Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1575413 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1403860 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1514891 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1627684 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1656325 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1473746 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1528471 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1464956 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1485786 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1452472 (Python Code)

Max Activating Token Index: 240

Text #10

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1536324 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1486457 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1376698 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1655305 (Python Code)

Max Activating Token Index: 901

Text #14

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1488564 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1387508 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1255926 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1467927 (Python Code)

Max Activating Token Index: 471

Text #18

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1375729 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1361942 (Python Code)

Max Activating Token Index: 449