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

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

Neuron 5972 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.7972. Min Act: -0.0002

Data Index: 1563171 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.7635. Min Act: -0.0002

Data Index: 1653184 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.7935. Min Act: -0.0002

Data Index: 1464427 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.7445. Min Act: -0.0002

Data Index: 1420312 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6908. Min Act: -0.0002

Data Index: 1511882 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6890. Min Act: -0.0002

Data Index: 1561347 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6833. Min Act: -0.0002

Data Index: 1587954 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6105. Min Act: -0.0002

Data Index: 1572548 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6093. Min Act: -0.0002

Data Index: 1614243 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6622. Min Act: -0.0002

Data Index: 1575919 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.5904. Min Act: -0.0002

Data Index: 1557325 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6063. Min Act: -0.0002

Data Index: 1444732 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6365. Min Act: -0.0002

Data Index: 1557840 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6078. Min Act: -0.0002

Data Index: 1640747 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6342. Min Act: -0.0002

Data Index: 1510581 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.6273. Min Act: -0.0002

Data Index: 1508341 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.5957. Min Act: -0.0002

Data Index: 1376403 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.5804. Min Act: -0.0002

Data Index: 1606156 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.5751. Min Act: -0.0002

Data Index: 1390376 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 1.7972. Min Range: -1.7972

Max Act: 1.5499. Min Act: -0.0002

Data Index: 1502325 (Python Code)

Max Activating Token Index: 848