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

Dataset: The Pile

Neuron 111 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: 0.7570. Min Range: -0.7570

Max Act: 0.6750. Min Act: -0.0000

Data Index: 521947 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1144468 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7236. Min Act: -0.0000

Data Index: 369992 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1397193 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7004. Min Act: -0.0000

Data Index: 885333 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6915. Min Act: -0.0000

Data Index: 992837 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1658359 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1318738 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7176. Min Act: -0.0000

Data Index: 165185 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7058. Min Act: -0.0000

Data Index: 785316 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1857025 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1098882 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1990360 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6591. Min Act: -0.0000

Data Index: 621614 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6232. Min Act: -0.0000

Data Index: 992134 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1151967 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6579. Min Act: -0.0000

Data Index: 566940 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6171. Min Act: -0.0000

Data Index: 334716 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1756548 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5898. Min Act: -0.0000

Data Index: 60112 (The Pile)

Max Activating Token Index: 37