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

Dataset: The Pile

Neuron 414 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: 1.1366. Min Range: -1.1366

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1506357 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1774316 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1081336 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8847. Min Act: -0.0000

Data Index: 245483 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1640652 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1731871 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8127. Min Act: -0.0000

Data Index: 927451 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1163871 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8391. Min Act: -0.0000

Data Index: 177328 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1091684 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1535705 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7391. Min Act: -0.0000

Data Index: 598981 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1426020 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7735. Min Act: -0.0000

Data Index: 434282 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1172592 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1952963 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.6896. Min Act: -0.0000

Data Index: 24125 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7205. Min Act: -0.0000

Data Index: 827045 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1745827 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1933693 (The Pile)

Max Activating Token Index: 66