Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2238 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2911. Min Act: -0.0001

Data Index: 84456 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1123088 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2853. Min Act: -0.0001

Data Index: 490543 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2714. Min Act: -0.0001

Data Index: 30538 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2748. Min Act: -0.0001

Data Index: 259363 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2850. Min Act: -0.0001

Data Index: 440841 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2648. Min Act: -0.0001

Data Index: 207495 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2737. Min Act: -0.0001

Data Index: 42802 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2625. Min Act: -0.0001

Data Index: 159876 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2528. Min Act: -0.0001

Data Index: 135510 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2434. Min Act: -0.0001

Data Index: 631850 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2571. Min Act: -0.0001

Data Index: 683842 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2427. Min Act: -0.0001

Data Index: 841853 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2113. Min Act: -0.0001

Data Index: 327983 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2298. Min Act: -0.0001

Data Index: 302189 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2340. Min Act: -0.0001

Data Index: 157984 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2432. Min Act: -0.0001

Data Index: 514736 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1239589 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2201. Min Act: -0.0001

Data Index: 226596 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2429. Min Act: -0.0001

Data Index: 666828 (C4 (Web Text))

Max Activating Token Index: 758