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

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

Neuron 4861 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0002

Data Index: 571551 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0607. Min Act: -0.0003

Data Index: 683018 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0616. Min Act: -0.0003

Data Index: 649431 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1164047 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0611. Min Act: -0.0003

Data Index: 71224 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0588. Min Act: -0.0002

Data Index: 330993 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0597. Min Act: -0.0003

Data Index: 366419 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0594. Min Act: -0.0002

Data Index: 15803 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0605. Min Act: -0.0003

Data Index: 193065 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0581. Min Act: -0.0002

Data Index: 910725 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0574. Min Act: -0.0003

Data Index: 739604 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0581. Min Act: -0.0003

Data Index: 405850 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1145248 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0561. Min Act: -0.0003

Data Index: 418876 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0562. Min Act: -0.0003

Data Index: 649956 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1233505 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0558. Min Act: -0.0003

Data Index: 276908 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1337563 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0566. Min Act: -0.0003

Data Index: 434374 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0537. Min Act: -0.0003

Data Index: 116872 (C4 (Web Text))

Max Activating Token Index: 105