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

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

Neuron 3232 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: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1497704 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1537580 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1590244 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1449968 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1601961 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1465379 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1436724 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1503697 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1599917 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1523237 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1537665 (Python Code)

Max Activating Token Index: 798

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1600243 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1547095 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1384853 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1651837 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1487984 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1406886 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1527900 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1446866 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1559642 (Python Code)

Max Activating Token Index: 781