Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 424 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1017753 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6801. Min Act: 0.0000

Data Index: 379120 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1213071 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6176. Min Act: -0.0000

Data Index: 253468 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5971. Min Act: -0.0000

Data Index: 432626 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1614286 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1808531 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1768617 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1198600 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1715069 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5947. Min Act: 0.0001

Data Index: 146100 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6040. Min Act: 0.0001

Data Index: 46586 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5508. Min Act: 0.0000

Data Index: 843829 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5760. Min Act: 0.0002

Data Index: 1487977 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1505545 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5456. Min Act: -0.0000

Data Index: 293861 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5959. Min Act: -0.0000

Data Index: 566416 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1907913 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5672. Min Act: -0.0000

Data Index: 536650 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5246. Min Act: -0.0000

Data Index: 842579 (The Pile)

Max Activating Token Index: 424