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

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

Neuron 3880 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5743. Min Act: -0.0001

Data Index: 696198 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5822. Min Act: -0.0002

Data Index: 458303 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5426. Min Act: -0.0002

Data Index: 1184233 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4325. Min Act: -0.0002

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5121. Min Act: -0.0001

Data Index: 190256 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5334. Min Act: -0.0002

Data Index: 46883 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5503. Min Act: -0.0001

Data Index: 368612 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4579. Min Act: -0.0001

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4863. Min Act: -0.0002

Data Index: 1039724 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5110. Min Act: -0.0001

Data Index: 982616 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5138. Min Act: -0.0002

Data Index: 1148751 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5063. Min Act: -0.0002

Data Index: 720718 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1014216 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5079. Min Act: -0.0001

Data Index: 233290 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5021. Min Act: -0.0001

Data Index: 53234 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4927. Min Act: -0.0001

Data Index: 711629 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4640. Min Act: -0.0002

Data Index: 1248390 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.5043. Min Act: -0.0002

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4788. Min Act: -0.0002

Data Index: 644159 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.5822. Min Range: -0.5822

Max Act: 0.4765. Min Act: -0.0002

Data Index: 490054 (C4 (Web Text))

Max Activating Token Index: 586