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

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

Neuron 5988 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.6014. Min Act: -0.0000

Data Index: 552233 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1189457 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4858. Min Act: -0.0000

Data Index: 106524 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4762. Min Act: -0.0000

Data Index: 724598 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4570. Min Act: -0.0000

Data Index: 682722 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1273215 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.5072. Min Act: -0.0000

Data Index: 168484 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.6013. Min Act: -0.0000

Data Index: 43465 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.5150. Min Act: -0.0000

Data Index: 229070 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4772. Min Act: 0.0000

Data Index: 1272165 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4885. Min Act: -0.0000

Data Index: 308144 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4981. Min Act: -0.0000

Data Index: 851310 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4501. Min Act: -0.0000

Data Index: 490683 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4385. Min Act: 0.0000

Data Index: 568369 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4490. Min Act: -0.0000

Data Index: 471496 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1338807 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4365. Min Act: -0.0000

Data Index: 2978 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4014. Min Act: -0.0000

Data Index: 558206 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4115. Min Act: -0.0000

Data Index: 432275 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.6014. Min Range: -0.6014

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1095111 (C4 (Web Text))

Max Activating Token Index: 208