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

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

Neuron 2796 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: 665572 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0025. Min Act: -0.0002

Data Index: 28095 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 556702 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1308983 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0003

Data Index: 261450 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 522813 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0023. Min Act: -0.0002

Data Index: 846149 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 35810 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0003

Data Index: 1110048 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 950402 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0002

Data Index: 316431 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0002

Data Index: 1248401 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0003

Data Index: 455834 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 430603 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 24927 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0002

Data Index: 891678 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1186546 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 160972 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0018. Min Act: -0.0002

Data Index: 842230 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 941861 (C4 (Web Text))

Max Activating Token Index: 590