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

Dataset: The Pile

Neuron 3026 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1421196 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.6708. Min Act: -0.0000

Data Index: 676244 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1723676 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1234784 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1176733 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1768595 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1529881 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5136. Min Act: -0.0000

Data Index: 368492 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1683435 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5423. Min Act: -0.0000

Data Index: 507030 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1178904 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4773. Min Act: -0.0000

Data Index: 306345 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4641. Min Act: -0.0000

Data Index: 56773 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4700. Min Act: -0.0000

Data Index: 604386 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4313. Min Act: -0.0000

Data Index: 935021 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4546. Min Act: -0.0000

Data Index: 390809 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1284197 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1087350 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1537291 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4256. Min Act: -0.0000

Data Index: 811922 (The Pile)

Max Activating Token Index: 38