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

Dataset: The Pile

Neuron 1797 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: 6.6013. Min Range: -6.6013

Max Act: 6.6013. Min Act: -0.0000

Data Index: 711610 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.8898. Min Act: -0.0000

Data Index: 1817706 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.5778. Min Act: -0.0000

Data Index: 932067 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.6469. Min Act: -0.0000

Data Index: 186075 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.6227. Min Act: -0.0000

Data Index: 1453219 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4488. Min Act: -0.0000

Data Index: 1378854 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.2452. Min Act: -0.0000

Data Index: 1751664 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4189. Min Act: -0.0000

Data Index: 1558437 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.3980. Min Act: -0.0000

Data Index: 1950852 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4131. Min Act: -0.0000

Data Index: 1228453 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.5018. Min Act: -0.0000

Data Index: 1812640 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.2956. Min Act: -0.0000

Data Index: 1281261 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.1102. Min Act: -0.0000

Data Index: 1936580 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.8058. Min Act: -0.0000

Data Index: 1788390 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4487. Min Act: -0.0000

Data Index: 878072 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4597. Min Act: -0.0000

Data Index: 674803 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.2699. Min Act: -0.0000

Data Index: 28194 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 6.6013. Min Range: -6.6013

Max Act: 4.9038. Min Act: -0.0000

Data Index: 354498 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.4283. Min Act: -0.0000

Data Index: 1442917 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 6.6013. Min Range: -6.6013

Max Act: 5.2454. Min Act: -0.0000

Data Index: 1195151 (The Pile)

Max Activating Token Index: 575