Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 823 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0004

Data Index: 816723 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1086. Min Act: -0.0005

Data Index: 143921 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1031. Min Act: -0.0005

Data Index: 914832 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1046. Min Act: -0.0005

Data Index: 372087 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0958. Min Act: -0.0005

Data Index: 754186 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0929. Min Act: -0.0004

Data Index: 9753 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0918. Min Act: -0.0005

Data Index: 819219 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0889. Min Act: -0.0005

Data Index: 179878 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0971. Min Act: -0.0004

Data Index: 613255 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0943. Min Act: -0.0005

Data Index: 1147658 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0913. Min Act: -0.0005

Data Index: 972451 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0894. Min Act: -0.0004

Data Index: 1252642 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0911. Min Act: -0.0005

Data Index: 465939 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0837. Min Act: -0.0005

Data Index: 206449 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0801. Min Act: -0.0005

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0876. Min Act: -0.0005

Data Index: 960148 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0829. Min Act: -0.0005

Data Index: 22506 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0828. Min Act: -0.0005

Data Index: 285759 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0848. Min Act: -0.0004

Data Index: 1040636 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0795. Min Act: -0.0005

Data Index: 269069 (C4 (Web Text))

Max Activating Token Index: 949