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

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

Neuron 2612 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: 0.0000

Data Index: 87253 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0571. Min Act: -0.0000

Data Index: 412925 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0518. Min Act: 0.0000

Data Index: 1040961 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0533. Min Act: 0.0000

Data Index: 5900 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0525. Min Act: 0.0000

Data Index: 677466 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0535. Min Act: -0.0000

Data Index: 249023 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0491. Min Act: 0.0000

Data Index: 293296 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0507. Min Act: -0.0000

Data Index: 245665 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0484. Min Act: -0.0000

Data Index: 919542 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0502. Min Act: -0.0000

Data Index: 660947 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1132600 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: 0.0000

Data Index: 212842 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0494. Min Act: -0.0000

Data Index: 725713 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: 0.0000

Data Index: 1002456 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0491. Min Act: -0.0000

Data Index: 33478 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1343926 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0474. Min Act: 0.0001

Data Index: 714655 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1003331 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0447. Min Act: -0.0000

Data Index: 480532 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0455. Min Act: 0.0000

Data Index: 619471 (C4 (Web Text))

Max Activating Token Index: 475