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

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

Neuron 287 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: 0.8683. Min Range: -0.8683

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1580764 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1638260 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1647929 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1594596 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1571980 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1511428 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1509878 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1620141 (Python Code)

Max Activating Token Index: 471

Text #8

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1629484 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1540294 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1612296 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1581857 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1576788 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1471267 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1523427 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1425672 (Python Code)

Max Activating Token Index: 889

Text #16

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1387068 (Python Code)

Max Activating Token Index: 226

Text #17

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1560263 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1422880 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1577986 (Python Code)

Max Activating Token Index: 469