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

Dataset: The Pile

Neuron 1000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1708160 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1027166 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1277160 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.8406. Min Act: -0.0000

Data Index: 630440 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7544. Min Act: -0.0000

Data Index: 443333 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1563996 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1246784 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1166336 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7028. Min Act: -0.0000

Data Index: 522753 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1575319 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1534899 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1799334 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7009. Min Act: -0.0000

Data Index: 288789 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.7479. Min Act: -0.0000

Data Index: 258825 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1961791 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1789404 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1878799 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6700. Min Act: -0.0000

Data Index: 643895 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1150065 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1816808 (The Pile)

Max Activating Token Index: 143