Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1927 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.7168. Min Act: -0.0001

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6646. Min Act: -0.0001

Data Index: 598072 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6308. Min Act: -0.0001

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6131. Min Act: -0.0000

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5771. Min Act: -0.0001

Data Index: 69166 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6031. Min Act: -0.0001

Data Index: 99806 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5597. Min Act: -0.0001

Data Index: 1137033 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1330911 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1322736 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5621. Min Act: -0.0001

Data Index: 284246 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5656. Min Act: -0.0001

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5673. Min Act: -0.0001

Data Index: 412192 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5685. Min Act: -0.0000

Data Index: 329214 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5657. Min Act: -0.0001

Data Index: 557107 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5343. Min Act: -0.0001

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5485. Min Act: -0.0001

Data Index: 182125 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5344. Min Act: -0.0001

Data Index: 153788 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5341. Min Act: -0.0001

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5547. Min Act: -0.0001

Data Index: 350974 (C4 (Web Text))

Max Activating Token Index: 990