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

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

Neuron 2279 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.4040. Min Act: -0.0000

Data Index: 460508 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3535. Min Act: -0.0000

Data Index: 809762 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3565. Min Act: -0.0000

Data Index: 908821 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1124983 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3087. Min Act: -0.0000

Data Index: 916611 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3009. Min Act: -0.0000

Data Index: 798261 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3096. Min Act: -0.0000

Data Index: 483467 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2947. Min Act: -0.0000

Data Index: 527418 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1012936 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2886. Min Act: 0.0000

Data Index: 471723 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3065. Min Act: -0.0000

Data Index: 188479 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3014. Min Act: -0.0000

Data Index: 935500 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2906. Min Act: -0.0000

Data Index: 227971 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3042. Min Act: -0.0000

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2758. Min Act: -0.0000

Data Index: 634152 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2908. Min Act: 0.0000

Data Index: 96034 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2774. Min Act: -0.0000

Data Index: 198936 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1018832 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2619. Min Act: -0.0000

Data Index: 481165 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1020902 (C4 (Web Text))

Max Activating Token Index: 710