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

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

Neuron 355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2073. Min Range: -2.2073

Max Act: 2.2073. Min Act: -0.0000

Data Index: 287576 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 2.2073. Min Range: -2.2073

Max Act: 2.2046. Min Act: -0.0000

Data Index: 96391 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 2.2073. Min Range: -2.2073

Max Act: 2.0427. Min Act: -0.0000

Data Index: 975361 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 2.2073. Min Range: -2.2073

Max Act: 2.0329. Min Act: -0.0000

Data Index: 461740 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.8954. Min Act: -0.0000

Data Index: 867498 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 2.2073. Min Range: -2.2073

Max Act: 2.0914. Min Act: -0.0000

Data Index: 713229 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.9377. Min Act: -0.0000

Data Index: 608865 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.7155. Min Act: -0.0000

Data Index: 893351 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.7651. Min Act: -0.0000

Data Index: 544241 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.7299. Min Act: -0.0000

Data Index: 705591 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.7057. Min Act: -0.0000

Data Index: 647764 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.6537. Min Act: -0.0000

Data Index: 175422 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1264737 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.6298. Min Act: -0.0000

Data Index: 224690 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.5609. Min Act: -0.0000

Data Index: 37512 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.5494. Min Act: -0.0000

Data Index: 425841 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.5466. Min Act: -0.0000

Data Index: 70537 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.6809. Min Act: -0.0000

Data Index: 44053 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.5868. Min Act: -0.0000

Data Index: 31780 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.2073. Min Range: -2.2073

Max Act: 1.5368. Min Act: -0.0000

Data Index: 993990 (C4 (Web Text))

Max Activating Token Index: 991