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

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

Neuron 624 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.5549. Min Act: -0.0000

Data Index: 1543951 (Python Code)

Max Activating Token Index: 54

Text #1

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.5463. Min Act: -0.0000

Data Index: 1584482 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.1661. Min Act: -0.0000

Data Index: 1449920 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.4534. Min Act: -0.0000

Data Index: 1652539 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.1335. Min Act: -0.0000

Data Index: 1562132 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 4.5549. Min Range: -4.5549

Max Act: 4.0058. Min Act: -0.0000

Data Index: 1622515 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.8058. Min Act: -0.0000

Data Index: 1496569 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.9360. Min Act: -0.0000

Data Index: 1551282 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.7882. Min Act: -0.0000

Data Index: 1419207 (Python Code)

Max Activating Token Index: 491

Text #9

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.7302. Min Act: -0.0000

Data Index: 1573317 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.7120. Min Act: -0.0000

Data Index: 1652307 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.6209. Min Act: -0.0000

Data Index: 1575724 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.6113. Min Act: -0.0000

Data Index: 1467714 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.6040. Min Act: -0.0000

Data Index: 1535078 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.5009. Min Act: -0.0000

Data Index: 1497971 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.6185. Min Act: -0.0000

Data Index: 1443304 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.5209. Min Act: -0.0000

Data Index: 1546433 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.5151. Min Act: -0.0000

Data Index: 1551970 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.6484. Min Act: -0.0000

Data Index: 1494110 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 4.5549. Min Range: -4.5549

Max Act: 3.5642. Min Act: -0.0000

Data Index: 1486422 (Python Code)

Max Activating Token Index: 616