Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1267 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 445125 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4893. Min Act: -0.0000

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4923. Min Act: -0.0000

Data Index: 261871 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4679. Min Act: -0.0000

Data Index: 514482 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4649. Min Act: -0.0000

Data Index: 180346 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4500. Min Act: -0.0000

Data Index: 923702 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4520. Min Act: -0.0000

Data Index: 299925 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4407. Min Act: -0.0000

Data Index: 960075 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4142. Min Act: -0.0000

Data Index: 913312 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4285. Min Act: -0.0000

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4251. Min Act: -0.0000

Data Index: 11202 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4227. Min Act: -0.0000

Data Index: 842247 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1253838 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4460. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4046. Min Act: -0.0000

Data Index: 174353 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1204533 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4279. Min Act: -0.0000

Data Index: 832574 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3849. Min Act: 0.0000

Data Index: 1154753 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4277. Min Act: -0.0000

Data Index: 342456 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3930. Min Act: -0.0000

Data Index: 164350 (C4 (Web Text))

Max Activating Token Index: 993