Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1829 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0004

Data Index: 659194 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0004

Data Index: 802991 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 94337 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1607350 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 676952 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1272847 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1212852 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1408996 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0004

Data Index: 1136169 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 98454 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 388464 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1451106 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1518927 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1538064 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0003

Data Index: 244369 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1583749 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0003

Data Index: 1374852 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0004

Data Index: 1261987 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0004

Data Index: 1177948 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0003

Data Index: 99348 (C4 (Web Text))

Max Activating Token Index: 758