Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1691 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5387. Min Range: -2.5387

Max Act: 2.5387. Min Act: -0.0000

Data Index: 85122 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.9143. Min Act: -0.0000

Data Index: 200389 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.7029. Min Act: -0.0000

Data Index: 978287 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.6655. Min Act: -0.0000

Data Index: 656078 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.5789. Min Act: -0.0000

Data Index: 901372 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.6530. Min Act: -0.0000

Data Index: 168586 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.5393. Min Act: -0.0000

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.6084. Min Act: -0.0000

Data Index: 901198 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4256. Min Act: -0.0000

Data Index: 434169 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.7887. Min Act: -0.0000

Data Index: 316353 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.5621. Min Act: -0.0000

Data Index: 576605 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.6550. Min Act: -0.0000

Data Index: 154182 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4689. Min Act: -0.0000

Data Index: 343274 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.6218. Min Act: -0.0000

Data Index: 494449 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1191956 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4034. Min Act: -0.0000

Data Index: 915571 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4781. Min Act: -0.0000

Data Index: 160397 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.3422. Min Act: -0.0000

Data Index: 542206 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1316649 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 2.5387. Min Range: -2.5387

Max Act: 1.4994. Min Act: -0.0000

Data Index: 371332 (C4 (Web Text))

Max Activating Token Index: 529