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

Dataset: The Pile

Neuron 2301 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.5474. Min Act: -0.0000

Data Index: 297106 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.4059. Min Act: -0.0000

Data Index: 416998 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.2590. Min Act: -0.0000

Data Index: 1800671 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.3536. Min Act: -0.0000

Data Index: 1672268 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.5406. Min Act: -0.0000

Data Index: 1381344 (The Pile)

Max Activating Token Index: 315

Text #5

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.8829. Min Act: -0.0000

Data Index: 1982848 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 11.5474. Min Range: -11.5474

Max Act: 8.6433. Min Act: -0.0000

Data Index: 1256455 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.5450. Min Act: -0.0000

Data Index: 1280630 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.1792. Min Act: -0.0000

Data Index: 688499 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.7350. Min Act: -0.0000

Data Index: 354479 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 11.5474. Min Range: -11.5474

Max Act: 9.5968. Min Act: -0.0000

Data Index: 210536 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 11.5474. Min Range: -11.5474

Max Act: 9.7877. Min Act: -0.0000

Data Index: 1362449 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 11.5474. Min Range: -11.5474

Max Act: 9.7634. Min Act: -0.0000

Data Index: 918785 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.1430. Min Act: -0.0000

Data Index: 147872 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 11.5474. Min Range: -11.5474

Max Act: 9.6668. Min Act: -0.0000

Data Index: 328134 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.5442. Min Act: -0.0000

Data Index: 1972955 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.9963. Min Act: -0.0000

Data Index: 1401710 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 11.5474. Min Range: -11.5474

Max Act: 11.1718. Min Act: -0.0000

Data Index: 1628860 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.7300. Min Act: -0.0000

Data Index: 320982 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 11.5474. Min Range: -11.5474

Max Act: 10.0952. Min Act: -0.0000

Data Index: 86126 (The Pile)

Max Activating Token Index: 602