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

Dataset: The Pile

Neuron 3764 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: 5.1894. Min Range: -5.1894

Max Act: 5.1894. Min Act: -0.0000

Data Index: 358271 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.9074. Min Act: -0.0000

Data Index: 882270 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.8844. Min Act: -0.0000

Data Index: 1841170 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.8508. Min Act: -0.0000

Data Index: 1299917 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.4844. Min Act: -0.0000

Data Index: 1371446 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.6018. Min Act: -0.0000

Data Index: 1173912 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3687. Min Act: -0.0000

Data Index: 1760680 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.1552. Min Act: -0.0000

Data Index: 918994 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3246. Min Act: -0.0000

Data Index: 1809686 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3231. Min Act: -0.0000

Data Index: 1377641 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3100. Min Act: -0.0000

Data Index: 920859 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.6332. Min Act: -0.0000

Data Index: 1085452 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.2391. Min Act: -0.0000

Data Index: 1223195 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3926. Min Act: -0.0000

Data Index: 304506 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.7177. Min Act: -0.0000

Data Index: 584989 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3515. Min Act: -0.0000

Data Index: 1917405 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.3424. Min Act: -0.0000

Data Index: 1251239 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.0992. Min Act: -0.0000

Data Index: 1580988 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 5.1894. Min Range: -5.1894

Max Act: 3.9166. Min Act: -0.0000

Data Index: 93389 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 5.1894. Min Range: -5.1894

Max Act: 4.2539. Min Act: -0.0000

Data Index: 1280648 (The Pile)

Max Activating Token Index: 149