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

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

Neuron 812 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.5527. Min Act: -0.0000

Data Index: 831085 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.8862. Min Act: -0.0000

Data Index: 400167 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.3987. Min Act: -0.0000

Data Index: 110764 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4174. Min Act: -0.0000

Data Index: 700998 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.5909. Min Act: -0.0000

Data Index: 450836 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.6575. Min Act: -0.0000

Data Index: 210555 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4668. Min Act: -0.0000

Data Index: 532903 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4694. Min Act: -0.0000

Data Index: 1298287 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.3900. Min Act: -0.0000

Data Index: 2674 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4311. Min Act: -0.0000

Data Index: 460096 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.2556. Min Act: -0.0000

Data Index: 474497 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.5524. Min Act: -0.0000

Data Index: 172952 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4339. Min Act: -0.0000

Data Index: 846034 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.2066. Min Act: -0.0000

Data Index: 861845 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.3793. Min Act: -0.0000

Data Index: 296882 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4076. Min Act: -0.0000

Data Index: 925863 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.3861. Min Act: -0.0000

Data Index: 194351 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.4128. Min Act: -0.0000

Data Index: 1125795 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.2410. Min Act: -0.0000

Data Index: 1031750 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 7.8862. Min Range: -7.8862

Max Act: 7.2051. Min Act: -0.0000

Data Index: 694850 (C4 (Web Text))

Max Activating Token Index: 836