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

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

Neuron 69 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0028. Min Act: -0.0006

Data Index: 819923 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0029. Min Act: -0.0006

Data Index: 456514 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0027. Min Act: -0.0006

Data Index: 1310939 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 897712 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0027. Min Act: -0.0006

Data Index: 643297 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1040425 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 9448 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0021. Min Act: -0.0006

Data Index: 760580 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 843209 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1230623 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 382612 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0024. Min Act: -0.0006

Data Index: 354218 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0023. Min Act: -0.0006

Data Index: 1282206 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0024. Min Act: -0.0006

Data Index: 590274 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1244688 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0023. Min Act: -0.0006

Data Index: 321610 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1175604 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1215300 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0023. Min Act: -0.0006

Data Index: 1182312 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0024. Min Act: -0.0006

Data Index: 717088 (C4 (Web Text))

Max Activating Token Index: 175