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

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

Neuron 1780 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1163136 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0680. Min Act: -0.0002

Data Index: 405589 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0667. Min Act: -0.0002

Data Index: 392443 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 536372 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0593. Min Act: -0.0002

Data Index: 26581 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0647. Min Act: -0.0002

Data Index: 349686 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0586. Min Act: -0.0002

Data Index: 82848 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1016755 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0557. Min Act: -0.0002

Data Index: 43742 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0601. Min Act: -0.0002

Data Index: 403232 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1219933 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0559. Min Act: -0.0002

Data Index: 375233 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0543. Min Act: -0.0002

Data Index: 519359 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0659. Min Act: -0.0002

Data Index: 180039 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0558. Min Act: -0.0002

Data Index: 30827 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1356909 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1349318 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1034520 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0530. Min Act: -0.0002

Data Index: 361099 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1335295 (C4 (Web Text))

Max Activating Token Index: 557