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

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

Neuron 4991 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1566931 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1455182 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1445183 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0312. Min Act: -0.0003

Data Index: 513655 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1614652 (Python Code)

Max Activating Token Index: 665

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0303. Min Act: -0.0003

Data Index: 257328 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1566892 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1221807 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0292. Min Act: -0.0003

Data Index: 669584 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1650601 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0289. Min Act: -0.0003

Data Index: 760009 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1478240 (Python Code)

Max Activating Token Index: 883

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0263. Min Act: -0.0003

Data Index: 75286 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1068181 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1385634 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0267. Min Act: -0.0002

Data Index: 582079 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0259. Min Act: -0.0003

Data Index: 761085 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1641915 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1376139 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0261. Min Act: -0.0003

Data Index: 858663 (C4 (Web Text))

Max Activating Token Index: 842