Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0000

Data Index: 527799 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1019319 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1208407 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0651. Min Act: -0.0000

Data Index: 449758 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1045221 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0620. Min Act: -0.0000

Data Index: 50747 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0640. Min Act: -0.0000

Data Index: 265866 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0616. Min Act: -0.0000

Data Index: 791527 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0613. Min Act: -0.0000

Data Index: 424222 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0609. Min Act: -0.0000

Data Index: 42731 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1188672 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0597. Min Act: -0.0001

Data Index: 427261 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0590. Min Act: -0.0000

Data Index: 738963 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1191423 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0564. Min Act: -0.0000

Data Index: 607455 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0581. Min Act: -0.0001

Data Index: 592375 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1111972 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0561. Min Act: -0.0000

Data Index: 55535 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1305442 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0585. Min Act: -0.0000

Data Index: 999001 (C4 (Web Text))

Max Activating Token Index: 946