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

Dataset: The Pile

Neuron 357 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.8308. Min Act: -0.0000

Data Index: 925292 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.5607. Min Act: -0.0000

Data Index: 1195774 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7035. Min Act: -0.0000

Data Index: 1771753 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.5335. Min Act: -0.0000

Data Index: 43080 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.7178. Min Act: -0.0000

Data Index: 1778887 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.3306. Min Act: -0.0000

Data Index: 597749 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.1520. Min Act: -0.0000

Data Index: 1935590 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.2009. Min Act: -0.0000

Data Index: 21127 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.1516. Min Act: -0.0000

Data Index: 181690 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.4826. Min Act: -0.0000

Data Index: 1231910 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.3344. Min Act: -0.0000

Data Index: 68391 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.0640. Min Act: 0.0000

Data Index: 254365 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.1211. Min Act: 0.0000

Data Index: 1080772 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 3.8308. Min Range: -3.8308

Max Act: 3.1368. Min Act: -0.0000

Data Index: 870214 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.9954. Min Act: -0.0000

Data Index: 1642542 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.8222. Min Act: -0.0000

Data Index: 1061955 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.6258. Min Act: -0.0000

Data Index: 474317 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.8325. Min Act: -0.0000

Data Index: 1760805 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.6656. Min Act: -0.0000

Data Index: 1241124 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 3.8308. Min Range: -3.8308

Max Act: 2.8421. Min Act: -0.0000

Data Index: 1138425 (The Pile)

Max Activating Token Index: 255