Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2602 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0026. Min Act: -0.0002

Data Index: 284643 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 610711 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 711860 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1098875 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 354023 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 256280 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 724360 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0003

Data Index: 568863 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 588423 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1070687 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 530257 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 947637 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 950292 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1252273 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 165688 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 132921 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 152925 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 408713 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1047856 (C4 (Web Text))

Max Activating Token Index: 691