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

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

Neuron 784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1456549 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.3574. Min Act: -0.0000

Data Index: 1419981 (Python Code)

Max Activating Token Index: 645

Text #2

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.4615. Min Act: -0.0000

Data Index: 1379381 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1515802 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.0609. Min Act: -0.0000

Data Index: 1490912 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.2797. Min Act: -0.0000

Data Index: 1379873 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.1086. Min Act: -0.0000

Data Index: 1467109 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.3008. Min Act: -0.0000

Data Index: 1598580 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.0535. Min Act: -0.0000

Data Index: 1654723 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1538677 (Python Code)

Max Activating Token Index: 396

Text #10

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.9562. Min Act: -0.0000

Data Index: 1452113 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1474368 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1499998 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.0880. Min Act: -0.0000

Data Index: 1440851 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 2.5656. Min Range: -2.5656

Max Act: 2.1752. Min Act: -0.0000

Data Index: 1421051 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.8512. Min Act: -0.0000

Data Index: 1590499 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.8327. Min Act: -0.0000

Data Index: 1488654 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.8118. Min Act: -0.0000

Data Index: 1455490 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1611181 (Python Code)

Max Activating Token Index: 331

Text #19

Max Range: 2.5656. Min Range: -2.5656

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1375498 (Python Code)

Max Activating Token Index: 911