Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2368 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.7024. Min Act: -0.0001

Data Index: 1516050 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6935. Min Act: -0.0001

Data Index: 1474903 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6386. Min Act: -0.0001

Data Index: 1608418 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1545465 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5448. Min Act: -0.0001

Data Index: 1433374 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1389179 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1407715 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6079. Min Act: -0.0001

Data Index: 1532422 (Python Code)

Max Activating Token Index: 859

Text #8

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1577292 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1401674 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6272. Min Act: -0.0001

Data Index: 1384281 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1448995 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5874. Min Act: -0.0001

Data Index: 1625098 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1473057 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5486. Min Act: -0.0001

Data Index: 1509700 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1574257 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5564. Min Act: -0.0001

Data Index: 1512789 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5473. Min Act: -0.0001

Data Index: 1538138 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1455233 (Python Code)

Max Activating Token Index: 590

Text #19

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1377224 (Python Code)

Max Activating Token Index: 876