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

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

Neuron 4382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2387. Min Range: -5.2387

Max Act: 5.2387. Min Act: -0.0000

Data Index: 1192961 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 5.2387. Min Range: -5.2387

Max Act: 4.7841. Min Act: -0.0000

Data Index: 206315 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 5.2387. Min Range: -5.2387

Max Act: 4.3189. Min Act: -0.0000

Data Index: 260096 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 5.2387. Min Range: -5.2387

Max Act: 4.0878. Min Act: -0.0000

Data Index: 597432 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.8159. Min Act: -0.0000

Data Index: 880460 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.6267. Min Act: -0.0000

Data Index: 1040140 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.8058. Min Act: -0.0000

Data Index: 234002 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.2421. Min Act: -0.0000

Data Index: 572669 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.6382. Min Act: -0.0000

Data Index: 907559 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.4492. Min Act: -0.0000

Data Index: 889551 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.1039. Min Act: -0.0000

Data Index: 220782 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.1048. Min Act: -0.0000

Data Index: 25762 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.2404. Min Act: -0.0000

Data Index: 277602 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.5618. Min Act: -0.0000

Data Index: 181998 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.5382. Min Act: -0.0000

Data Index: 57125 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.3860. Min Act: -0.0000

Data Index: 279687 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.0565. Min Act: -0.0000

Data Index: 376844 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 5.2387. Min Range: -5.2387

Max Act: 2.9807. Min Act: -0.0000

Data Index: 894563 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 5.2387. Min Range: -5.2387

Max Act: 3.1160. Min Act: -0.0000

Data Index: 624993 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 5.2387. Min Range: -5.2387

Max Act: 2.9827. Min Act: -0.0000

Data Index: 761622 (C4 (Web Text))

Max Activating Token Index: 858