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

Dataset: The Pile

Neuron 5033 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.2296. Min Act: -0.0000

Data Index: 846192 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1874364 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.3121. Min Act: -0.0000

Data Index: 635473 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1265672 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1525. Min Act: -0.0000

Data Index: 866124 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1495. Min Act: -0.0000

Data Index: 500675 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0150. Min Act: -0.0000

Data Index: 945567 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1488. Min Act: -0.0000

Data Index: 937036 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0250. Min Act: -0.0000

Data Index: 647311 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1699591 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1567837 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9986. Min Act: -0.0000

Data Index: 631943 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1333231 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0852. Min Act: -0.0000

Data Index: 263572 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1608743 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1296274 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1499441 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9889. Min Act: -0.0000

Data Index: 689045 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1720400 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9102. Min Act: -0.0000

Data Index: 633556 (The Pile)

Max Activating Token Index: 221