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

Dataset: The Pile

Neuron 806 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: 7.7218. Min Range: -7.7218

Max Act: 7.7218. Min Act: -0.0000

Data Index: 1520933 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 7.7218. Min Range: -7.7218

Max Act: 7.2703. Min Act: -0.0000

Data Index: 571993 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 7.7218. Min Range: -7.7218

Max Act: 7.1866. Min Act: -0.0000

Data Index: 1177852 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 7.7218. Min Range: -7.7218

Max Act: 7.2130. Min Act: -0.0000

Data Index: 1071097 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.8166. Min Act: -0.0000

Data Index: 1477813 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2049. Min Act: -0.0000

Data Index: 768117 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.4946. Min Act: -0.0000

Data Index: 1719737 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.4407. Min Act: -0.0000

Data Index: 1356761 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 7.7218. Min Range: -7.7218

Max Act: 7.0286. Min Act: -0.0000

Data Index: 155323 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.5007. Min Act: -0.0000

Data Index: 351797 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.5480. Min Act: -0.0000

Data Index: 1784183 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2926. Min Act: -0.0000

Data Index: 1382765 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 7.7218. Min Range: -7.7218

Max Act: 5.8079. Min Act: -0.0000

Data Index: 461855 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2475. Min Act: -0.0000

Data Index: 370262 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2666. Min Act: -0.0000

Data Index: 1467804 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.3589. Min Act: -0.0000

Data Index: 1172224 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.3421. Min Act: -0.0000

Data Index: 1385697 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 7.7218. Min Range: -7.7218

Max Act: 4.0167. Min Act: -0.0000

Data Index: 1546609 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2439. Min Act: -0.0000

Data Index: 1279798 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 7.7218. Min Range: -7.7218

Max Act: 6.2898. Min Act: -0.0000

Data Index: 1356826 (The Pile)

Max Activating Token Index: 386