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

Dataset: The Pile

Neuron 3054 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: 0.6231. Min Range: -0.6231

Max Act: 0.5694. Min Act: -0.0000

Data Index: 443545 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1717073 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5495. Min Act: -0.0000

Data Index: 152055 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5076. Min Act: -0.0000

Data Index: 830196 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1549569 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5898. Min Act: -0.0000

Data Index: 42409 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5254. Min Act: -0.0000

Data Index: 966058 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1301908 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4441. Min Act: -0.0000

Data Index: 511315 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5246. Min Act: -0.0000

Data Index: 962793 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1263491 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1054210 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4780. Min Act: -0.0000

Data Index: 664682 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1523970 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1389421 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4978. Min Act: -0.0000

Data Index: 397447 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1845979 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4955. Min Act: -0.0000

Data Index: 657156 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4474. Min Act: -0.0000

Data Index: 382749 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4380. Min Act: -0.0000

Data Index: 250280 (The Pile)

Max Activating Token Index: 348