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

Dataset: The Pile

Neuron 721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1368205 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6226. Min Act: -0.0000

Data Index: 343386 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5771. Min Act: -0.0000

Data Index: 66048 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5115. Min Act: -0.0000

Data Index: 937550 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1512370 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5368. Min Act: -0.0000

Data Index: 967081 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5266. Min Act: -0.0000

Data Index: 778493 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5326. Min Act: -0.0000

Data Index: 89556 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5043. Min Act: -0.0000

Data Index: 588867 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1685399 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1664296 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1843040 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.5543. Min Act: -0.0000

Data Index: 249542 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1167274 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1710914 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1267204 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1698624 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4412. Min Act: -0.0000

Data Index: 444296 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1999474 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1679213 (The Pile)

Max Activating Token Index: 388