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

Dataset: The Pile

Neuron 3323 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: 0.7518. Min Range: -0.7518

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1377768 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1409272 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1634748 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1044052 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6684. Min Act: -0.0000

Data Index: 159741 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6585. Min Act: -0.0000

Data Index: 918879 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6431. Min Act: -0.0000

Data Index: 215790 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6088. Min Act: -0.0000

Data Index: 266183 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6290. Min Act: -0.0000

Data Index: 705728 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1195010 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1238136 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5680. Min Act: -0.0000

Data Index: 712111 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1509032 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1617496 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5603. Min Act: -0.0000

Data Index: 229452 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1791202 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5988. Min Act: -0.0000

Data Index: 111221 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5787. Min Act: -0.0000

Data Index: 472347 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5270. Min Act: -0.0000

Data Index: 302779 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5892. Min Act: -0.0000

Data Index: 859401 (The Pile)

Max Activating Token Index: 760