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

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

Neuron 2534 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.5304. Min Act: -0.0000

Data Index: 40383 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1524335 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4718. Min Act: -0.0000

Data Index: 26949 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4759. Min Act: -0.0000

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4885. Min Act: -0.0000

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1157694 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4629. Min Act: -0.0000

Data Index: 634369 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1005128 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4246. Min Act: -0.0000

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4354. Min Act: -0.0000

Data Index: 381504 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4172. Min Act: -0.0000

Data Index: 508648 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4348. Min Act: -0.0000

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4564. Min Act: -0.0000

Data Index: 697303 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4187. Min Act: -0.0000

Data Index: 454636 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4144. Min Act: -0.0000

Data Index: 823453 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3568. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4148. Min Act: -0.0000

Data Index: 539275 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3779. Min Act: -0.0000

Data Index: 561617 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4351. Min Act: -0.0000

Data Index: 832868 (C4 (Web Text))

Max Activating Token Index: 421