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

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

Neuron 4418 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.6121. Min Act: -0.0000

Data Index: 1505043 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.5548. Min Act: -0.0000

Data Index: 1392469 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.2368. Min Act: -0.0000

Data Index: 582004 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.5565. Min Act: -0.0000

Data Index: 533164 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.2848. Min Act: -0.0000

Data Index: 1614300 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.3127. Min Act: -0.0000

Data Index: 1310851 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.2810. Min Act: -0.0000

Data Index: 1418123 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.0631. Min Act: -0.0000

Data Index: 1387427 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.0311. Min Act: -0.0000

Data Index: 1278008 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.3278. Min Act: -0.0000

Data Index: 1530287 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 5.6121. Min Range: -5.6121

Max Act: 4.9448. Min Act: -0.0000

Data Index: 1368662 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.4887. Min Act: -0.0000

Data Index: 1549247 (Python Code)

Max Activating Token Index: 932

Text #12

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.3051. Min Act: -0.0000

Data Index: 1450604 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.2871. Min Act: -0.0000

Data Index: 1580252 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.0553. Min Act: -0.0000

Data Index: 1599489 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.0478. Min Act: -0.0000

Data Index: 1576540 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 5.6121. Min Range: -5.6121

Max Act: 4.9527. Min Act: -0.0000

Data Index: 1460607 (Python Code)

Max Activating Token Index: 920

Text #17

Max Range: 5.6121. Min Range: -5.6121

Max Act: 4.7547. Min Act: -0.0000

Data Index: 1442484 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 5.6121. Min Range: -5.6121

Max Act: 5.0251. Min Act: -0.0000

Data Index: 1408458 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 5.6121. Min Range: -5.6121

Max Act: 4.9927. Min Act: -0.0000

Data Index: 1626129 (Python Code)

Max Activating Token Index: 848