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

Dataset: The Pile

Neuron 2275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.3369. Min Act: -0.0000

Data Index: 378580 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.3183. Min Act: -0.0000

Data Index: 245026 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.3439. Min Act: -0.0000

Data Index: 1499855 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1151. Min Act: -0.0000

Data Index: 190335 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1410279 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1495742 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1093647 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1294153 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1852297 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1781558 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1363958 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1124368 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1357494 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.0891. Min Act: -0.0000

Data Index: 479771 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1559999 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1911190 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1427. Min Act: -0.0000

Data Index: 455764 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.1088. Min Act: -0.0000

Data Index: 929823 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.3439. Min Range: -1.3439

Max Act: 1.0186. Min Act: -0.0000

Data Index: 90450 (The Pile)

Max Activating Token Index: 924

Text #19

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1659011 (The Pile)

Max Activating Token Index: 991