Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2503 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.2500. Min Act: -0.0002

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.1773. Min Act: -0.0002

Data Index: 415280 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.1677. Min Act: -0.0002

Data Index: 1142108 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.1055. Min Act: -0.0002

Data Index: 1036417 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0805. Min Act: -0.0002

Data Index: 1044665 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0776. Min Act: -0.0002

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0596. Min Act: -0.0002

Data Index: 1323821 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0573. Min Act: -0.0002

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0558. Min Act: -0.0002

Data Index: 1346750 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0275. Min Act: -0.0002

Data Index: 1315094 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0343. Min Act: -0.0002

Data Index: 551581 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0171. Min Act: -0.0002

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0375. Min Act: -0.0002

Data Index: 98684 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0420. Min Act: -0.0002

Data Index: 1312257 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0048. Min Act: -0.0002

Data Index: 677650 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0021. Min Act: -0.0001

Data Index: 1164715 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0068. Min Act: -0.0002

Data Index: 166344 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0134. Min Act: -0.0002

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 1.2500. Min Range: -1.2500

Max Act: 1.0016. Min Act: -0.0002

Data Index: 330608 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.2500. Min Range: -1.2500

Max Act: 0.9954. Min Act: -0.0002

Data Index: 1346934 (C4 (Web Text))

Max Activating Token Index: 726