Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.4839. Min Act: -0.0000

Data Index: 1524246 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.3160. Min Act: -0.0000

Data Index: 1571594 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.0311. Min Act: -0.0000

Data Index: 1382500 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.3342. Min Act: -0.0000

Data Index: 1599312 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.1973. Min Act: -0.0000

Data Index: 1451807 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.1358. Min Act: -0.0000

Data Index: 1522567 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.9820. Min Act: -0.0001

Data Index: 1487848 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.8098. Min Act: -0.0001

Data Index: 1432169 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 2.4839. Min Range: -2.4839

Max Act: 2.0343. Min Act: -0.0001

Data Index: 1615055 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.9177. Min Act: -0.0001

Data Index: 1597650 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.8622. Min Act: -0.0000

Data Index: 1451113 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.8370. Min Act: -0.0001

Data Index: 1650456 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1394249 (Python Code)

Max Activating Token Index: 125

Text #13

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.9290. Min Act: -0.0000

Data Index: 1635161 (Python Code)

Max Activating Token Index: 660

Text #14

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.8819. Min Act: -0.0001

Data Index: 1544699 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.9039. Min Act: -0.0001

Data Index: 1363553 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1443788 (Python Code)

Max Activating Token Index: 861

Text #17

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.8873. Min Act: -0.0000

Data Index: 1384186 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.7887. Min Act: -0.0000

Data Index: 1398700 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 2.4839. Min Range: -2.4839

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1615209 (Python Code)

Max Activating Token Index: 932