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

Dataset: The Pile

Neuron 2027 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1384500 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7301. Min Act: -0.0000

Data Index: 637944 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7272. Min Act: -0.0000

Data Index: 376972 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1107360 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1790231 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1221143 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6809. Min Act: -0.0000

Data Index: 429466 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6846. Min Act: -0.0000

Data Index: 224138 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1968788 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1356869 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6444. Min Act: -0.0000

Data Index: 267682 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1150384 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6216. Min Act: -0.0000

Data Index: 449736 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6077. Min Act: -0.0000

Data Index: 44372 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1003753 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5504. Min Act: -0.0000

Data Index: 686250 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5337. Min Act: -0.0000

Data Index: 478915 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5766. Min Act: -0.0000

Data Index: 674008 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5832. Min Act: -0.0000

Data Index: 523776 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.7636. Min Range: -0.7636

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1735799 (The Pile)

Max Activating Token Index: 799