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

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

Neuron 1376 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0000

Data Index: 236646 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0776. Min Act: -0.0000

Data Index: 639993 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0801. Min Act: -0.0000

Data Index: 431729 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0747. Min Act: -0.0000

Data Index: 782765 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1209091 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1218293 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0707. Min Act: -0.0000

Data Index: 792884 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0662. Min Act: -0.0000

Data Index: 744202 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0716. Min Act: -0.0000

Data Index: 491174 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0689. Min Act: -0.0000

Data Index: 52757 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0661. Min Act: -0.0000

Data Index: 275832 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0673. Min Act: -0.0000

Data Index: 741653 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0695. Min Act: -0.0000

Data Index: 96836 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0692. Min Act: -0.0000

Data Index: 307966 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0639. Min Act: -0.0000

Data Index: 948873 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0649. Min Act: -0.0000

Data Index: 640172 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0649. Min Act: -0.0000

Data Index: 636889 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1106607 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0621. Min Act: -0.0000

Data Index: 641444 (C4 (Web Text))

Max Activating Token Index: 14