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

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

Neuron 1282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.8827. Min Act: -0.0001

Data Index: 958288 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.8221. Min Act: -0.0000

Data Index: 976561 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.7674. Min Act: -0.0000

Data Index: 61626 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.6837. Min Act: -0.0000

Data Index: 1135412 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.6208. Min Act: -0.0001

Data Index: 7381 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.6179. Min Act: -0.0001

Data Index: 396790 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.5698. Min Act: -0.0001

Data Index: 716672 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4880. Min Act: -0.0000

Data Index: 45896 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1045418 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4937. Min Act: -0.0000

Data Index: 567436 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.5019. Min Act: -0.0001

Data Index: 1064715 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4926. Min Act: -0.0000

Data Index: 1347371 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4929. Min Act: -0.0000

Data Index: 837588 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4180. Min Act: -0.0001

Data Index: 436177 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4081. Min Act: -0.0000

Data Index: 961109 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4503. Min Act: -0.0000

Data Index: 587436 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.3882. Min Act: -0.0001

Data Index: 295226 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4289. Min Act: -0.0000

Data Index: 307894 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.4258. Min Act: -0.0000

Data Index: 76573 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.8827. Min Range: -1.8827

Max Act: 1.3522. Min Act: -0.0001

Data Index: 1185027 (C4 (Web Text))

Max Activating Token Index: 479