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

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

Neuron 574 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7533. Min Act: -0.0000

Data Index: 1376768 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7267. Min Act: -0.0000

Data Index: 1593688 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1574403 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1592774 (Python Code)

Max Activating Token Index: 600

Text #4

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1541637 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1405444 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1424011 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.6656. Min Act: -0.0001

Data Index: 1370390 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7192. Min Act: -0.0001

Data Index: 1555011 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1564556 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1550266 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1626403 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1423828 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1522246 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1478775 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4912. Min Act: -0.0001

Data Index: 1433543 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1368379 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1477811 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4348. Min Act: -0.0001

Data Index: 1638254 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1382018 (Python Code)

Max Activating Token Index: 864