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

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

Neuron 5808 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: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1149499 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0848. Min Act: -0.0002

Data Index: 180939 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1107012 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0757. Min Act: -0.0002

Data Index: 87125 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0751. Min Act: -0.0002

Data Index: 766905 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0733. Min Act: -0.0002

Data Index: 961632 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0731. Min Act: -0.0002

Data Index: 327465 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1351237 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1166497 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0709. Min Act: -0.0002

Data Index: 403522 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0731. Min Act: -0.0002

Data Index: 229847 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0710. Min Act: -0.0002

Data Index: 624725 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1030758 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0708. Min Act: -0.0002

Data Index: 233939 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0701. Min Act: -0.0002

Data Index: 199730 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1038753 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0690. Min Act: -0.0002

Data Index: 267356 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0672. Min Act: -0.0002

Data Index: 78570 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0682. Min Act: -0.0002

Data Index: 310790 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1046038 (C4 (Web Text))

Max Activating Token Index: 107