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

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

Neuron 1821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1573738 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2257. Min Act: -0.0001

Data Index: 103154 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1179928 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0980. Min Act: -0.0001

Data Index: 934450 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0931. Min Act: -0.0001

Data Index: 668486 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1350039 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0960. Min Act: -0.0001

Data Index: 120060 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0991. Min Act: -0.0000

Data Index: 820357 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0861. Min Act: -0.0001

Data Index: 626598 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0937. Min Act: -0.0001

Data Index: 179347 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0869. Min Act: -0.0000

Data Index: 303492 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0976. Min Act: -0.0000

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0911. Min Act: -0.0001

Data Index: 237279 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1640861 (Python Code)

Max Activating Token Index: 836

Text #15

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0919. Min Act: -0.0000

Data Index: 259580 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1142324 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0911. Min Act: -0.0000

Data Index: 579080 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1214881 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.3019. Min Range: -0.3019

Max Act: 0.0907. Min Act: -0.0000

Data Index: 47894 (C4 (Web Text))

Max Activating Token Index: 994