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

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

Neuron 1170 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2287. Min Range: -5.2287

Max Act: 5.2287. Min Act: -0.0000

Data Index: 1005168 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 5.2287. Min Range: -5.2287

Max Act: 5.1248. Min Act: -0.0000

Data Index: 1095798 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 5.2287. Min Range: -5.2287

Max Act: 5.2176. Min Act: -0.0000

Data Index: 400413 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.8850. Min Act: -0.0000

Data Index: 769139 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.5340. Min Act: -0.0000

Data Index: 215569 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.6108. Min Act: -0.0000

Data Index: 1286127 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.6269. Min Act: -0.0000

Data Index: 391926 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.3450. Min Act: -0.0000

Data Index: 85946 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.2863. Min Act: -0.0000

Data Index: 951157 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.4346. Min Act: -0.0000

Data Index: 119323 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.2440. Min Act: -0.0000

Data Index: 781937 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.1039. Min Act: -0.0000

Data Index: 389513 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 5.2287. Min Range: -5.2287

Max Act: 3.7781. Min Act: -0.0000

Data Index: 470552 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.0539. Min Act: -0.0000

Data Index: 221124 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.1594. Min Act: -0.0000

Data Index: 372764 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.2287. Min Range: -5.2287

Max Act: 3.9739. Min Act: -0.0000

Data Index: 290764 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.4646. Min Act: -0.0000

Data Index: 434471 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 5.2287. Min Range: -5.2287

Max Act: 4.1217. Min Act: -0.0000

Data Index: 435498 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 5.2287. Min Range: -5.2287

Max Act: 3.7707. Min Act: -0.0000

Data Index: 174847 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 5.2287. Min Range: -5.2287

Max Act: 3.8812. Min Act: -0.0000

Data Index: 731117 (C4 (Web Text))

Max Activating Token Index: 62