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

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

Neuron 14 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: 0.0609. Min Range: -0.0609

Max Act: 0.0601. Min Act: -0.0002

Data Index: 104801 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1059882 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0604. Min Act: -0.0002

Data Index: 283430 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 634239 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0561. Min Act: -0.0002

Data Index: 73798 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0601. Min Act: -0.0002

Data Index: 997352 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1237665 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0585. Min Act: -0.0002

Data Index: 421549 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0466. Min Act: -0.0002

Data Index: 623841 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1108915 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0554. Min Act: -0.0002

Data Index: 374513 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1259956 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0565. Min Act: -0.0002

Data Index: 880836 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0564. Min Act: -0.0002

Data Index: 894475 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0505. Min Act: -0.0002

Data Index: 883626 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0548. Min Act: -0.0002

Data Index: 636046 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0527. Min Act: -0.0002

Data Index: 980173 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0547. Min Act: -0.0002

Data Index: 643009 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1034668 (C4 (Web Text))

Max Activating Token Index: 845