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

Dataset: The Pile

Neuron 5036 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.6444. Min Act: -0.0000

Data Index: 252732 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.5699. Min Act: -0.0000

Data Index: 1494568 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.9130. Min Act: -0.0000

Data Index: 1462102 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.5012. Min Act: -0.0000

Data Index: 243681 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.2021. Min Act: -0.0000

Data Index: 775862 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.3349. Min Act: -0.0000

Data Index: 960243 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.2439. Min Act: -0.0000

Data Index: 737916 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0558. Min Act: -0.0000

Data Index: 1079051 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.2366. Min Act: -0.0000

Data Index: 708576 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0197. Min Act: -0.0000

Data Index: 191446 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0052. Min Act: -0.0000

Data Index: 1235073 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.1772. Min Act: -0.0000

Data Index: 497523 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0107. Min Act: -0.0000

Data Index: 1445506 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.3574. Min Act: -0.0000

Data Index: 1012691 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.1219. Min Act: -0.0000

Data Index: 873281 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 5.9130. Min Range: -5.9130

Max Act: 4.9271. Min Act: -0.0000

Data Index: 1805254 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.3027. Min Act: -0.0000

Data Index: 1571715 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0621. Min Act: -0.0000

Data Index: 1162877 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.0232. Min Act: -0.0000

Data Index: 480033 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 5.9130. Min Range: -5.9130

Max Act: 4.7838. Min Act: -0.0000

Data Index: 1018770 (The Pile)

Max Activating Token Index: 443