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

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

Neuron 1212 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1591432 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1727. Min Act: -0.0003

Data Index: 1512969 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1500. Min Act: -0.0002

Data Index: 1433496 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1509137 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1552. Min Act: -0.0003

Data Index: 1568911 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1488. Min Act: -0.0003

Data Index: 1588267 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1468. Min Act: -0.0003

Data Index: 1553560 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1571177 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1532452 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1424. Min Act: -0.0003

Data Index: 1575095 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1419. Min Act: -0.0002

Data Index: 1506956 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1421. Min Act: -0.0003

Data Index: 1458575 (Python Code)

Max Activating Token Index: 526

Text #12

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1472. Min Act: -0.0003

Data Index: 1655616 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1470. Min Act: -0.0002

Data Index: 1650844 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1414. Min Act: -0.0002

Data Index: 1406631 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1438. Min Act: -0.0003

Data Index: 1458372 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1494. Min Act: -0.0003

Data Index: 1599649 (Python Code)

Max Activating Token Index: 584

Text #17

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1494. Min Act: -0.0003

Data Index: 1634590 (Python Code)

Max Activating Token Index: 486

Text #18

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1485. Min Act: -0.0003

Data Index: 1415046 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1599102 (Python Code)

Max Activating Token Index: 551