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

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

Neuron 3412 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.8523. Min Act: -0.0001

Data Index: 1573392 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6767. Min Act: -0.0001

Data Index: 1541732 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.6714. Min Act: -0.0001

Data Index: 1425643 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.5595. Min Act: -0.0001

Data Index: 1413771 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.5955. Min Act: -0.0001

Data Index: 1375661 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.5432. Min Act: -0.0001

Data Index: 1576262 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4541. Min Act: -0.0001

Data Index: 1622730 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4103. Min Act: -0.0001

Data Index: 1526373 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1637131 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4786. Min Act: -0.0001

Data Index: 1601306 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4299. Min Act: -0.0001

Data Index: 1609462 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4269. Min Act: -0.0001

Data Index: 1644874 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4142. Min Act: -0.0001

Data Index: 1530866 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1449527 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4002. Min Act: -0.0001

Data Index: 1641136 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.3607. Min Act: -0.0001

Data Index: 1499543 (Python Code)

Max Activating Token Index: 314

Text #16

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4385. Min Act: -0.0001

Data Index: 1428786 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4417. Min Act: -0.0001

Data Index: 1614510 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.3533. Min Act: -0.0001

Data Index: 1375632 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 1.8523. Min Range: -1.8523

Max Act: 1.4297. Min Act: -0.0001

Data Index: 1444623 (Python Code)

Max Activating Token Index: 276