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

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

Neuron 632 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0577. Min Range: -6.0577

Max Act: 5.8714. Min Act: -0.0000

Data Index: 21550 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 6.0577. Min Range: -6.0577

Max Act: 6.0577. Min Act: -0.0000

Data Index: 1656819 (Python Code)

Max Activating Token Index: 242

Text #2

Max Range: 6.0577. Min Range: -6.0577

Max Act: 5.5766. Min Act: -0.0000

Data Index: 430178 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 6.0577. Min Range: -6.0577

Max Act: 5.7010. Min Act: -0.0000

Data Index: 841691 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 6.0577. Min Range: -6.0577

Max Act: 5.2783. Min Act: -0.0000

Data Index: 1066474 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 6.0577. Min Range: -6.0577

Max Act: 5.2558. Min Act: -0.0000

Data Index: 420613 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.8994. Min Act: -0.0000

Data Index: 1063591 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.7596. Min Act: -0.0000

Data Index: 340572 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.6763. Min Act: -0.0000

Data Index: 1335944 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.4618. Min Act: -0.0000

Data Index: 685760 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.9996. Min Act: -0.0000

Data Index: 1469399 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.6241. Min Act: -0.0000

Data Index: 996605 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.5651. Min Act: -0.0000

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.3602. Min Act: -0.0000

Data Index: 1311631 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.5209. Min Act: -0.0000

Data Index: 1298807 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.3430. Min Act: -0.0000

Data Index: 1203915 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.4717. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.6337. Min Act: -0.0000

Data Index: 367254 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.2201. Min Act: -0.0000

Data Index: 1341111 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 6.0577. Min Range: -6.0577

Max Act: 4.3814. Min Act: -0.0000

Data Index: 1061698 (C4 (Web Text))

Max Activating Token Index: 73