Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1518888 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1430266 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1425755 (Python Code)

Max Activating Token Index: 380

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1427001 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1367503 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1548834 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1546972 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1597067 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1437392 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1572704 (Python Code)

Max Activating Token Index: 435

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1610745 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1651352 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1473961 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1632855 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1461289 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1400037 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1555961 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1542470 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1431707 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1390867 (Python Code)

Max Activating Token Index: 294