Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1342490 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.9502. Min Act: -0.0000

Data Index: 657374 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8422. Min Act: -0.0000

Data Index: 616716 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1120343 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1080147 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1758369 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1664556 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7851. Min Act: -0.0000

Data Index: 114735 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1710620 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1004780 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1301018 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7127. Min Act: -0.0000

Data Index: 537134 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1418466 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7161. Min Act: -0.0000

Data Index: 677132 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1256598 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7501. Min Act: -0.0000

Data Index: 424007 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7315. Min Act: -0.0000

Data Index: 390069 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6724. Min Act: -0.0000

Data Index: 735656 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1643989 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6818. Min Act: -0.0000

Data Index: 69187 (The Pile)

Max Activating Token Index: 285