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

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

Neuron 2760 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5589. Min Act: -0.0001

Data Index: 951219 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1253897 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5541. Min Act: -0.0001

Data Index: 1265031 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5071. Min Act: -0.0001

Data Index: 631154 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5172. Min Act: -0.0001

Data Index: 474141 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5158. Min Act: -0.0000

Data Index: 335011 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4829. Min Act: -0.0000

Data Index: 122301 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5299. Min Act: -0.0000

Data Index: 475750 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4885. Min Act: -0.0000

Data Index: 58755 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4652. Min Act: -0.0001

Data Index: 289935 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4990. Min Act: -0.0001

Data Index: 348603 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5127. Min Act: -0.0001

Data Index: 167286 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4430. Min Act: -0.0000

Data Index: 971941 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4914. Min Act: -0.0001

Data Index: 206239 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1232260 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1107911 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1044272 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4678. Min Act: -0.0000

Data Index: 266955 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4763. Min Act: -0.0001

Data Index: 175780 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4694. Min Act: -0.0001

Data Index: 969681 (C4 (Web Text))

Max Activating Token Index: 798