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

Dataset: The Pile

Neuron 179 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: 0.2748. Min Range: -0.2748

Max Act: 0.2748. Min Act: -0.0000

Data Index: 17353 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2502. Min Act: -0.0000

Data Index: 347646 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1753. Min Act: -0.0000

Data Index: 996234 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1725989 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1848. Min Act: -0.0000

Data Index: 97579 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1717. Min Act: 0.0000

Data Index: 1519518 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1733673 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1250410 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1483. Min Act: -0.0000

Data Index: 355930 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1508. Min Act: -0.0000

Data Index: 823781 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1479. Min Act: 0.0000

Data Index: 271733 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1440. Min Act: -0.0000

Data Index: 990809 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1591. Min Act: -0.0000

Data Index: 512319 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1369. Min Act: -0.0000

Data Index: 611609 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1642022 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1875253 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1318. Min Act: -0.0000

Data Index: 680060 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1377. Min Act: -0.0000

Data Index: 864821 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1979270 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1408402 (The Pile)

Max Activating Token Index: 986