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

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

Neuron 5015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1445847 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1591846 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1459994 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1444471 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1377180 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1630995 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1548010 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1487307 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1467669 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1651480 (Python Code)

Max Activating Token Index: 1014

Text #10

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1580508 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1410804 (Python Code)

Max Activating Token Index: 962

Text #12

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1539720 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1543811 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1582241 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1636932 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1462197 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1544764 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1638466 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1460504 (Python Code)

Max Activating Token Index: 523