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

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

Neuron 315 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3609. Min Act: -0.0001

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3540. Min Act: -0.0001

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3342. Min Act: -0.0001

Data Index: 175164 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3233. Min Act: -0.0001

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3055. Min Act: -0.0001

Data Index: 160723 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3004. Min Act: -0.0001

Data Index: 626607 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2969. Min Act: -0.0001

Data Index: 556039 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2986. Min Act: -0.0001

Data Index: 201509 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.3073. Min Act: -0.0001

Data Index: 92027 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2866. Min Act: -0.0001

Data Index: 952707 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2923. Min Act: -0.0001

Data Index: 786492 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1179664 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1323945 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2721. Min Act: -0.0001

Data Index: 574371 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1124414 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2866. Min Act: -0.0001

Data Index: 211068 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2737. Min Act: -0.0001

Data Index: 833704 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2653. Min Act: -0.0001

Data Index: 753785 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.3644. Min Range: -0.3644

Max Act: 0.2830. Min Act: -0.0001

Data Index: 589808 (C4 (Web Text))

Max Activating Token Index: 970