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

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

Neuron 2461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1248800 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0002

Data Index: 406517 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0634. Min Act: -0.0002

Data Index: 735732 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0653. Min Act: -0.0002

Data Index: 48799 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1036575 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0607. Min Act: -0.0002

Data Index: 437102 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1251817 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1284124 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0560. Min Act: -0.0002

Data Index: 46853 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0596. Min Act: -0.0002

Data Index: 330837 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0544. Min Act: -0.0002

Data Index: 408553 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0563. Min Act: -0.0002

Data Index: 160776 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0569. Min Act: -0.0002

Data Index: 639567 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0553. Min Act: -0.0002

Data Index: 788803 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0552. Min Act: -0.0002

Data Index: 83608 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0547. Min Act: -0.0002

Data Index: 394308 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0565. Min Act: -0.0002

Data Index: 365871 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1142041 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0539. Min Act: -0.0002

Data Index: 149958 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0517. Min Act: -0.0002

Data Index: 320263 (C4 (Web Text))

Max Activating Token Index: 740