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

Dataset: The Pile

Neuron 436 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: 1.2220. Min Range: -1.2220

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1107348 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.2220. Min Act: -0.0000

Data Index: 981608 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1679727 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1117098 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1763789 (The Pile)

Max Activating Token Index: 954

Text #5

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.1058. Min Act: -0.0000

Data Index: 131520 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.0823. Min Act: -0.0000

Data Index: 76711 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.0353. Min Act: -0.0000

Data Index: 73325 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9495. Min Act: -0.0000

Data Index: 272029 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1296341 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 1.2220. Min Range: -1.2220

Max Act: 1.0079. Min Act: 0.0000

Data Index: 1125488 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9386. Min Act: -0.0000

Data Index: 800847 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1281001 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9718. Min Act: -0.0000

Data Index: 135230 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1893193 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1753506 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.8242. Min Act: -0.0000

Data Index: 152120 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.8602. Min Act: -0.0000

Data Index: 118621 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9127. Min Act: -0.0000

Data Index: 890738 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 1.2220. Min Range: -1.2220

Max Act: 0.9102. Min Act: -0.0000

Data Index: 312762 (The Pile)

Max Activating Token Index: 437