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

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

Neuron 5938 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.4936. Min Act: -0.0000

Data Index: 1612903 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.3442. Min Act: -0.0000

Data Index: 1373276 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.4582. Min Act: -0.0000

Data Index: 1499344 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.1562. Min Act: -0.0000

Data Index: 1414367 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1364825 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.1015. Min Act: -0.0000

Data Index: 1387799 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9735. Min Act: -0.0000

Data Index: 1379404 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9191. Min Act: -0.0000

Data Index: 1588327 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 2.4936. Min Range: -2.4936

Max Act: 2.0976. Min Act: -0.0000

Data Index: 1583461 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1468198 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9545. Min Act: -0.0000

Data Index: 1513620 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1395603 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9353. Min Act: -0.0000

Data Index: 1478736 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9324. Min Act: -0.0000

Data Index: 1595363 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.9233. Min Act: -0.0000

Data Index: 1633098 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.8978. Min Act: -0.0000

Data Index: 1626590 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1400841 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.7589. Min Act: -0.0000

Data Index: 1555065 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.8559. Min Act: -0.0000

Data Index: 1476778 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 2.4936. Min Range: -2.4936

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1386436 (Python Code)

Max Activating Token Index: 222