Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 255 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0024. Min Act: -0.0003

Data Index: 5670 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0023. Min Act: -0.0004

Data Index: 974605 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0023. Min Act: -0.0003

Data Index: 669813 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0003

Data Index: 1185255 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0023. Min Act: -0.0003

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0023. Min Act: -0.0004

Data Index: 894106 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0003

Data Index: 132474 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0004

Data Index: 1087298 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0003

Data Index: 721920 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 476915 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 340750 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0004

Data Index: 53337 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0004

Data Index: 326648 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0004

Data Index: 1213589 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0004

Data Index: 21280 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 563940 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 917676 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 1595132 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0021. Min Act: -0.0003

Data Index: 253581 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0020. Min Act: -0.0003

Data Index: 1214090 (C4 (Web Text))

Max Activating Token Index: 583