Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3390 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 2.5000. Min Range: -2.5000

Max Act: 2.5000. Min Act: -0.0000

Data Index: 1632453 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 2.5000. Min Range: -2.5000

Max Act: 2.2414. Min Act: -0.0000

Data Index: 1450811 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.9663. Min Act: -0.0000

Data Index: 120205 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.9020. Min Act: -0.0000

Data Index: 240966 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 2.5000. Min Range: -2.5000

Max Act: 2.1132. Min Act: -0.0000

Data Index: 122877 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.8845. Min Act: -0.0000

Data Index: 1564784 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.8832. Min Act: -0.0000

Data Index: 408316 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 2.5000. Min Range: -2.5000

Max Act: 2.0590. Min Act: -0.0000

Data Index: 1450855 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.9052. Min Act: -0.0000

Data Index: 1532448 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1335117 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7333. Min Act: -0.0000

Data Index: 1644192 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.8131. Min Act: -0.0000

Data Index: 980114 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7899. Min Act: -0.0000

Data Index: 788543 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7818. Min Act: -0.0000

Data Index: 539980 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7730. Min Act: -0.0000

Data Index: 304995 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1523505 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.6961. Min Act: -0.0000

Data Index: 316104 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.6594. Min Act: -0.0000

Data Index: 306104 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.7781. Min Act: -0.0000

Data Index: 1022211 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 2.5000. Min Range: -2.5000

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1839928 (The Pile)

Max Activating Token Index: 860