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

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

Neuron 5285 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: 1.8754. Min Range: -1.8754

Max Act: 1.8754. Min Act: -0.0000

Data Index: 1552066 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1629991 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1620995 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1408724 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1459237 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5746. Min Act: -0.0000

Data Index: 1555438 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.6551. Min Act: -0.0000

Data Index: 1529916 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1610563 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1483498 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1645748 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1388211 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.6651. Min Act: -0.0000

Data Index: 1420553 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1581363 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1366768 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1590809 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1452081 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1372345 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1521242 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1417701 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 1.8754. Min Range: -1.8754

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1360714 (Python Code)

Max Activating Token Index: 235