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

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

Neuron 1955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.7794. Min Act: -0.0000

Data Index: 1635170 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4508. Min Act: -0.0000

Data Index: 8052 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.5190. Min Act: -0.0000

Data Index: 60456 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3291. Min Act: -0.0000

Data Index: 1581106 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.9850. Min Act: -0.0000

Data Index: 1088697 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.0594. Min Act: -0.0000

Data Index: 1588075 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.7603. Min Act: -0.0000

Data Index: 444065 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.8179. Min Act: -0.0000

Data Index: 723727 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.7741. Min Act: -0.0000

Data Index: 369375 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.3430. Min Act: -0.0000

Data Index: 586488 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.7282. Min Act: -0.0000

Data Index: 61194 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.5493. Min Act: -0.0000

Data Index: 1279970 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.5351. Min Act: -0.0000

Data Index: 618828 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.6309. Min Act: -0.0000

Data Index: 415779 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.6208. Min Act: -0.0000

Data Index: 10775 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.7239. Min Act: -0.0000

Data Index: 728510 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.4554. Min Act: -0.0000

Data Index: 1251256 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.5867. Min Act: -0.0000

Data Index: 163599 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.3957. Min Act: -0.0000

Data Index: 1317257 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 3.7794. Min Range: -3.7794

Max Act: 2.3682. Min Act: -0.0000

Data Index: 189314 (C4 (Web Text))

Max Activating Token Index: 401