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

Dataset: The Pile

Neuron 2987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.2046. Min Act: -0.0000

Data Index: 815404 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1683507 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1821. Min Act: -0.0000

Data Index: 175630 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1331214 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1911159 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1700. Min Act: -0.0000

Data Index: 65680 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1587. Min Act: -0.0001

Data Index: 242535 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1848640 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1818342 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1941919 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1612. Min Act: -0.0000

Data Index: 369967 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1565. Min Act: -0.0000

Data Index: 492282 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1496. Min Act: -0.0000

Data Index: 638245 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1497. Min Act: -0.0000

Data Index: 351552 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1992753 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1516. Min Act: -0.0000

Data Index: 907315 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1501. Min Act: -0.0000

Data Index: 47374 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1430. Min Act: -0.0001

Data Index: 625743 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1309. Min Act: -0.0000

Data Index: 281873 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1544. Min Act: -0.0000

Data Index: 902285 (The Pile)

Max Activating Token Index: 348