Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0005

Data Index: 1566915 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0967. Min Act: -0.0005

Data Index: 1617598 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0951. Min Act: -0.0005

Data Index: 1574840 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0907. Min Act: -0.0005

Data Index: 1571108 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0901. Min Act: -0.0005

Data Index: 1603025 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0867. Min Act: -0.0005

Data Index: 1495017 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0903. Min Act: -0.0005

Data Index: 1577708 (Python Code)

Max Activating Token Index: 959

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0844. Min Act: -0.0005

Data Index: 1466230 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0866. Min Act: -0.0005

Data Index: 1571509 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0922. Min Act: -0.0005

Data Index: 1619037 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0872. Min Act: -0.0005

Data Index: 1435756 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0892. Min Act: -0.0005

Data Index: 1370063 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1593495 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0867. Min Act: -0.0005

Data Index: 1519707 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0829. Min Act: -0.0005

Data Index: 1535968 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0866. Min Act: -0.0005

Data Index: 1509993 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0859. Min Act: -0.0005

Data Index: 1454554 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0870. Min Act: -0.0005

Data Index: 1654728 (Python Code)

Max Activating Token Index: 816

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0873. Min Act: -0.0005

Data Index: 1636166 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0857. Min Act: -0.0005

Data Index: 1413412 (Python Code)

Max Activating Token Index: 595