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

Dataset: The Pile

Neuron 373 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: 1.0507. Min Range: -1.0507

Max Act: 1.0159. Min Act: -0.0000

Data Index: 296265 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0507. Min Act: -0.0000

Data Index: 525142 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1841335 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1148249 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9066. Min Act: -0.0000

Data Index: 195357 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1851682 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1076765 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8252. Min Act: -0.0000

Data Index: 511970 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8259. Min Act: -0.0000

Data Index: 624789 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1616882 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1974909 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1195420 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8598. Min Act: -0.0000

Data Index: 135816 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1779739 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8117. Min Act: -0.0000

Data Index: 589031 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1893919 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8422. Min Act: -0.0000

Data Index: 745207 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1088271 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7824. Min Act: -0.0000

Data Index: 794527 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1680540 (The Pile)

Max Activating Token Index: 919