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

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

Neuron 4882 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1609923 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.2994. Min Act: -0.0000

Data Index: 1612476 (Python Code)

Max Activating Token Index: 804

Text #2

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.2994. Min Act: 0.0000

Data Index: 1574544 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1650956 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1614. Min Act: 0.0000

Data Index: 1377571 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1715. Min Act: 0.0000

Data Index: 1469458 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1606. Min Act: 0.0000

Data Index: 1457812 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1628826 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1278. Min Act: 0.0000

Data Index: 1429913 (Python Code)

Max Activating Token Index: 466

Text #9

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1623430 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1536920 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1439471 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.0056. Min Act: 0.0000

Data Index: 1522352 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9972. Min Act: 0.0000

Data Index: 1509286 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1645240 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1516982 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9883. Min Act: 0.0000

Data Index: 1363565 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8163. Min Act: 0.0000

Data Index: 1616097 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1395880 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1453924 (Python Code)

Max Activating Token Index: 923