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

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

Neuron 2252 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0001

Data Index: 663554 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0319. Min Act: -0.0001

Data Index: 415131 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0329. Min Act: -0.0001

Data Index: 163700 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0269. Min Act: -0.0001

Data Index: 385114 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0291. Min Act: -0.0001

Data Index: 3293 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0276. Min Act: -0.0001

Data Index: 731843 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1215865 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1223563 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0261. Min Act: -0.0001

Data Index: 380890 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0243. Min Act: -0.0001

Data Index: 607119 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0268. Min Act: -0.0002

Data Index: 288937 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0239. Min Act: -0.0001

Data Index: 78580 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1289953 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0210. Min Act: -0.0001

Data Index: 395232 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1094581 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1178373 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0236. Min Act: -0.0001

Data Index: 938359 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0256. Min Act: -0.0001

Data Index: 54508 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1480961 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0220. Min Act: -0.0001

Data Index: 321995 (C4 (Web Text))

Max Activating Token Index: 298