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

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

Neuron 4773 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: 0.8556. Min Range: -0.8556

Max Act: 0.8556. Min Act: -0.0003

Data Index: 1070914 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8507. Min Act: -0.0002

Data Index: 289753 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8519. Min Act: -0.0002

Data Index: 1041883 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8313. Min Act: -0.0002

Data Index: 820454 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8330. Min Act: -0.0002

Data Index: 489134 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8149. Min Act: -0.0002

Data Index: 103112 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8037. Min Act: -0.0002

Data Index: 919153 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8215. Min Act: -0.0002

Data Index: 71470 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8219. Min Act: -0.0002

Data Index: 1257756 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7938. Min Act: -0.0002

Data Index: 201182 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7948. Min Act: -0.0002

Data Index: 829807 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7921. Min Act: -0.0002

Data Index: 1232028 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7810. Min Act: -0.0002

Data Index: 145443 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7812. Min Act: -0.0002

Data Index: 827736 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7645. Min Act: -0.0002

Data Index: 1033698 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7579. Min Act: -0.0002

Data Index: 910890 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7715. Min Act: -0.0003

Data Index: 1026251 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7650. Min Act: -0.0002

Data Index: 1213822 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7637. Min Act: -0.0002

Data Index: 1077674 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.7590. Min Act: -0.0002

Data Index: 1212063 (C4 (Web Text))

Max Activating Token Index: 18