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

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

Neuron 1062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0001

Data Index: 903764 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0689. Min Act: -0.0001

Data Index: 619160 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1161170 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0643. Min Act: -0.0001

Data Index: 2789 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1267341 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0589. Min Act: -0.0001

Data Index: 104917 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1121359 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0573. Min Act: -0.0001

Data Index: 150997 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1177537 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0545. Min Act: -0.0001

Data Index: 517954 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0539. Min Act: -0.0001

Data Index: 282580 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0580. Min Act: -0.0001

Data Index: 442321 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0564. Min Act: -0.0001

Data Index: 515373 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1070733 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1111657 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0492. Min Act: -0.0000

Data Index: 734422 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1267600 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0544. Min Act: -0.0001

Data Index: 522275 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1087851 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0540. Min Act: -0.0001

Data Index: 813769 (C4 (Web Text))

Max Activating Token Index: 744