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

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

Neuron 5886 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: -0.0000

Data Index: 30317 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8379. Min Act: -0.0000

Data Index: 911214 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7789. Min Act: -0.0000

Data Index: 424469 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7612. Min Act: -0.0000

Data Index: 996718 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1152975 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1402788 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1112598 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6108. Min Act: -0.0000

Data Index: 874381 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6454. Min Act: -0.0000

Data Index: 783114 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1204930 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1511922 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6162. Min Act: -0.0000

Data Index: 421551 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1481805 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1554629 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6236. Min Act: -0.0000

Data Index: 821478 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6299. Min Act: -0.0000

Data Index: 78874 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1557440 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1335806 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6189. Min Act: 0.0000

Data Index: 1478611 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.6370. Min Act: -0.0000

Data Index: 450882 (C4 (Web Text))

Max Activating Token Index: 740