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

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

Neuron 1032 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: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 574438 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 244403 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 43323 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 797764 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 991994 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 879162 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1273860 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1099295 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 418527 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 935632 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1176170 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 991908 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1145395 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1138566 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 181945 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 981127 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1226119 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 526479 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1135261 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 20589 (C4 (Web Text))

Max Activating Token Index: 618