Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 751 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4754. Min Range: -3.4754

Max Act: 3.4754. Min Act: -0.0001

Data Index: 39594 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.9896. Min Act: -0.0001

Data Index: 951942 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.7257. Min Act: -0.0000

Data Index: 3920 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.7447. Min Act: -0.0000

Data Index: 384828 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.4749. Min Act: -0.0001

Data Index: 1203385 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.4637. Min Act: -0.0001

Data Index: 237196 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.6921. Min Act: -0.0000

Data Index: 1174530 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.6495. Min Act: -0.0001

Data Index: 615747 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.6132. Min Act: -0.0000

Data Index: 765546 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.6103. Min Act: -0.0001

Data Index: 40688 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.7224. Min Act: -0.0001

Data Index: 1252203 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.5866. Min Act: -0.0000

Data Index: 1009142 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.5792. Min Act: -0.0001

Data Index: 368273 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.4453. Min Act: -0.0000

Data Index: 145891 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.4768. Min Act: -0.0001

Data Index: 183377 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.4318. Min Act: -0.0001

Data Index: 971763 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.3108. Min Act: -0.0000

Data Index: 461014 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.5480. Min Act: -0.0001

Data Index: 543737 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.3950. Min Act: -0.0000

Data Index: 252643 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.4754. Min Range: -3.4754

Max Act: 2.2636. Min Act: -0.0000

Data Index: 768707 (C4 (Web Text))

Max Activating Token Index: 606