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

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

Neuron 5843 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: 1.9474. Min Range: -1.9474

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1357868 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.8667. Min Act: -0.0000

Data Index: 722983 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.6936. Min Act: -0.0000

Data Index: 1608755 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.4163. Min Act: -0.0000

Data Index: 1551925 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.6474. Min Act: -0.0000

Data Index: 147541 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1371840 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1584130 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.5023. Min Act: -0.0000

Data Index: 941387 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.5441. Min Act: -0.0000

Data Index: 757312 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.7157. Min Act: -0.0000

Data Index: 892749 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1124864 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.4414. Min Act: -0.0000

Data Index: 886904 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1318005 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.4241. Min Act: -0.0000

Data Index: 579185 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.3596. Min Act: -0.0000

Data Index: 922353 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.2684. Min Act: -0.0000

Data Index: 577178 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.3193. Min Act: -0.0000

Data Index: 226029 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1644997 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.1955. Min Act: -0.0000

Data Index: 162688 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.9474. Min Range: -1.9474

Max Act: 1.3211. Min Act: -0.0000

Data Index: 918983 (C4 (Web Text))

Max Activating Token Index: 218