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

Dataset: The Pile

Neuron 2414 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: 0.7269. Min Range: -0.7269

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1349290 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4891. Min Act: -0.0000

Data Index: 719881 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5122. Min Act: -0.0000

Data Index: 466751 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1917470 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1548361 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4224. Min Act: -0.0000

Data Index: 268941 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4573. Min Act: -0.0000

Data Index: 405752 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1616511 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1504215 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4408. Min Act: -0.0000

Data Index: 660529 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4486. Min Act: -0.0000

Data Index: 545224 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1311136 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1592788 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4175. Min Act: -0.0000

Data Index: 489954 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1733861 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4135. Min Act: -0.0000

Data Index: 303668 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1310225 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1322862 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4068. Min Act: -0.0000

Data Index: 198506 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4201. Min Act: -0.0000

Data Index: 742919 (The Pile)

Max Activating Token Index: 345