Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3210 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5786. Min Range: -2.5786

Max Act: 2.5786. Min Act: -0.0000

Data Index: 974800 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1210845 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.4164. Min Act: -0.0000

Data Index: 680040 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.2788. Min Act: -0.0000

Data Index: 848216 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.4072. Min Act: -0.0000

Data Index: 143911 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.2120. Min Act: -0.0000

Data Index: 424723 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.2605. Min Act: -0.0000

Data Index: 368735 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.1850. Min Act: -0.0000

Data Index: 341907 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1107116 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.0879. Min Act: -0.0000

Data Index: 523460 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1170865 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.1101. Min Act: -0.0000

Data Index: 699626 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.0610. Min Act: -0.0000

Data Index: 443366 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9663. Min Act: -0.0000

Data Index: 499264 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9667. Min Act: -0.0000

Data Index: 903586 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1032111 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.5786. Min Range: -2.5786

Max Act: 1.0019. Min Act: -0.0000

Data Index: 689469 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1062789 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1025530 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 2.5786. Min Range: -2.5786

Max Act: 0.9009. Min Act: -0.0000

Data Index: 957776 (C4 (Web Text))

Max Activating Token Index: 679