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

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

Neuron 1184 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6414. Min Act: -0.0002

Data Index: 1505405 (Python Code)

Max Activating Token Index: 744

Text #1

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6300. Min Act: -0.0002

Data Index: 1581997 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6096. Min Act: -0.0002

Data Index: 1465594 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5982. Min Act: -0.0002

Data Index: 1464975 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5332. Min Act: -0.0002

Data Index: 1622919 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6433. Min Act: -0.0002

Data Index: 1501455 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6016. Min Act: -0.0002

Data Index: 1533681 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6098. Min Act: -0.0002

Data Index: 1541272 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5682. Min Act: -0.0002

Data Index: 1459469 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5520. Min Act: -0.0002

Data Index: 1408023 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6019. Min Act: -0.0002

Data Index: 1517962 (Python Code)

Max Activating Token Index: 831

Text #11

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5667. Min Act: -0.0002

Data Index: 1536026 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5509. Min Act: -0.0002

Data Index: 1512646 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5372. Min Act: -0.0002

Data Index: 1550875 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5051. Min Act: -0.0002

Data Index: 1655005 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4863. Min Act: -0.0002

Data Index: 1428040 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5493. Min Act: -0.0002

Data Index: 1523062 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5431. Min Act: -0.0002

Data Index: 1444120 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5291. Min Act: -0.0002

Data Index: 1598644 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5024. Min Act: -0.0002

Data Index: 1537644 (Python Code)

Max Activating Token Index: 880