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

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

Neuron 1649 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: 1.2853. Min Range: -1.2853

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1256922 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.1543. Min Act: -0.0000

Data Index: 585680 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1409497 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1540501 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.1243. Min Act: -0.0000

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1490216 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1067728 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.1132. Min Act: -0.0000

Data Index: 522543 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0875. Min Act: -0.0000

Data Index: 352772 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0668. Min Act: -0.0000

Data Index: 820588 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1649608 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1571004 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0220. Min Act: -0.0000

Data Index: 959348 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0173. Min Act: -0.0000

Data Index: 831303 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.2853. Min Range: -1.2853

Max Act: 0.9889. Min Act: -0.0000

Data Index: 644764 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.2853. Min Range: -1.2853

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1466886 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1629208 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 1.2853. Min Range: -1.2853

Max Act: 1.0158. Min Act: -0.0000

Data Index: 511319 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.2853. Min Range: -1.2853

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1616402 (Python Code)

Max Activating Token Index: 956

Text #19

Max Range: 1.2853. Min Range: -1.2853

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1531798 (Python Code)

Max Activating Token Index: 185