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

Dataset: The Pile

Neuron 1064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6128. Min Act: -0.0000

Data Index: 591794 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6214. Min Act: -0.0000

Data Index: 719326 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1265138 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5825. Min Act: -0.0000

Data Index: 515591 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5642. Min Act: -0.0000

Data Index: 511018 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5351. Min Act: -0.0000

Data Index: 884057 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1190551 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1508048 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4868. Min Act: -0.0000

Data Index: 415824 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5136. Min Act: -0.0000

Data Index: 544310 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1515025 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1288444 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5073. Min Act: -0.0000

Data Index: 149 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4849. Min Act: -0.0000

Data Index: 145818 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4986. Min Act: -0.0000

Data Index: 602726 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1532451 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4877. Min Act: -0.0000

Data Index: 973132 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1633288 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5127. Min Act: -0.0000

Data Index: 515885 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1479999 (The Pile)

Max Activating Token Index: 1020