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

Dataset: The Pile

Neuron 3231 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: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1078800 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2801. Min Act: -0.0000

Data Index: 348866 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1138563 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1706686 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2217. Min Act: -0.0000

Data Index: 530424 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2338. Min Act: -0.0000

Data Index: 868761 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2231. Min Act: -0.0000

Data Index: 263695 (The Pile)

Max Activating Token Index: 688

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2342. Min Act: -0.0000

Data Index: 856403 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1745721 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2301. Min Act: -0.0000

Data Index: 81410 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2350. Min Act: -0.0000

Data Index: 792659 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2339. Min Act: -0.0000

Data Index: 123867 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1788174 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1772611 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2212. Min Act: -0.0000

Data Index: 904428 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1300711 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2124. Min Act: -0.0000

Data Index: 521097 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1164411 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1785240 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1911. Min Act: -0.0000

Data Index: 584840 (The Pile)

Max Activating Token Index: 781