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

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

Neuron 3721 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: 0.6096. Min Range: -0.6096

Max Act: 0.6021. Min Act: -0.0002

Data Index: 545189 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.6096. Min Act: -0.0002

Data Index: 1297918 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5986. Min Act: -0.0002

Data Index: 499001 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.6042. Min Act: -0.0002

Data Index: 1312803 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5950. Min Act: -0.0002

Data Index: 393423 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5887. Min Act: -0.0002

Data Index: 947458 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5882. Min Act: -0.0002

Data Index: 1055585 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5987. Min Act: -0.0002

Data Index: 1189007 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5796. Min Act: -0.0002

Data Index: 241566 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5837. Min Act: -0.0002

Data Index: 645739 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5777. Min Act: -0.0002

Data Index: 406595 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5658. Min Act: -0.0002

Data Index: 102372 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5686. Min Act: -0.0002

Data Index: 1064584 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5643. Min Act: -0.0002

Data Index: 676082 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5600. Min Act: -0.0003

Data Index: 1305218 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5671. Min Act: -0.0002

Data Index: 965646 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5709. Min Act: -0.0002

Data Index: 640846 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5619. Min Act: -0.0002

Data Index: 544405 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5681. Min Act: -0.0002

Data Index: 739538 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.5485. Min Act: -0.0002

Data Index: 689943 (C4 (Web Text))

Max Activating Token Index: 76