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

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

Neuron 1130 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0002

Data Index: 345808 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1179232 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0854. Min Act: -0.0002

Data Index: 499601 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0815. Min Act: -0.0002

Data Index: 336042 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0839. Min Act: -0.0002

Data Index: 716119 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0828. Min Act: -0.0002

Data Index: 593556 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0816. Min Act: -0.0002

Data Index: 537351 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0769. Min Act: -0.0002

Data Index: 390934 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1239680 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0852. Min Act: -0.0002

Data Index: 778767 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0762. Min Act: -0.0002

Data Index: 982873 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0777. Min Act: -0.0002

Data Index: 489431 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1301711 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0777. Min Act: -0.0002

Data Index: 656863 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0771. Min Act: -0.0002

Data Index: 366359 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0742. Min Act: -0.0002

Data Index: 131539 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0743. Min Act: -0.0002

Data Index: 522702 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1108716 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0768. Min Act: -0.0002

Data Index: 644907 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0749. Min Act: -0.0002

Data Index: 980075 (C4 (Web Text))

Max Activating Token Index: 814