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

Dataset: The Pile

Neuron 2185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.3881. Min Act: -0.0000

Data Index: 206720 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.1960. Min Act: -0.0000

Data Index: 1264291 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.0054. Min Act: -0.0000

Data Index: 1548411 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.1878. Min Act: -0.0000

Data Index: 429669 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.1274. Min Act: -0.0000

Data Index: 1852627 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.0553. Min Act: -0.0000

Data Index: 1310700 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 5.3881. Min Range: -5.3881

Max Act: 5.2015. Min Act: -0.0000

Data Index: 196513 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.9905. Min Act: -0.0000

Data Index: 1629566 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.9619. Min Act: -0.0000

Data Index: 1657733 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.9109. Min Act: -0.0000

Data Index: 778521 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.9124. Min Act: -0.0000

Data Index: 1576147 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.7110. Min Act: -0.0000

Data Index: 1759751 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.5639. Min Act: -0.0000

Data Index: 45032 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.7630. Min Act: -0.0000

Data Index: 316044 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.7593. Min Act: -0.0000

Data Index: 1286690 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.7508. Min Act: -0.0000

Data Index: 74574 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.5786. Min Act: -0.0000

Data Index: 1722677 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.5460. Min Act: -0.0000

Data Index: 1847299 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.7129. Min Act: -0.0000

Data Index: 1189796 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 5.3881. Min Range: -5.3881

Max Act: 4.8880. Min Act: -0.0000

Data Index: 1803269 (The Pile)

Max Activating Token Index: 89