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

Dataset: The Pile

Neuron 2490 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: 0.6374. Min Range: -0.6374

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1672001 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1773583 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1304601 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5555. Min Act: -0.0000

Data Index: 979431 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5257. Min Act: -0.0000

Data Index: 72815 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5312. Min Act: -0.0000

Data Index: 721899 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1374545 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4971. Min Act: -0.0000

Data Index: 911862 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1323643 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1921696 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1177931 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4694. Min Act: -0.0000

Data Index: 901242 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4636. Min Act: -0.0000

Data Index: 555937 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1603645 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4876. Min Act: -0.0000

Data Index: 117414 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5326. Min Act: -0.0000

Data Index: 384832 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4801. Min Act: -0.0000

Data Index: 839535 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1330026 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1016555 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4917. Min Act: -0.0000

Data Index: 396669 (The Pile)

Max Activating Token Index: 519