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

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

Neuron 1322 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2354. Min Range: -4.2354

Max Act: 4.2354. Min Act: -0.0000

Data Index: 1401483 (Python Code)

Max Activating Token Index: 857

Text #1

Max Range: 4.2354. Min Range: -4.2354

Max Act: 4.0225. Min Act: -0.0000

Data Index: 1624430 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.9909. Min Act: -0.0000

Data Index: 1508306 (Python Code)

Max Activating Token Index: 456

Text #3

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.8225. Min Act: -0.0000

Data Index: 1550685 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 4.2354. Min Range: -4.2354

Max Act: 4.0531. Min Act: -0.0000

Data Index: 1643044 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.8145. Min Act: -0.0000

Data Index: 1417246 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.6749. Min Act: -0.0000

Data Index: 1482520 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.4479. Min Act: -0.0000

Data Index: 1461836 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.5934. Min Act: -0.0000

Data Index: 1552684 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.6126. Min Act: -0.0000

Data Index: 1497973 (Python Code)

Max Activating Token Index: 513

Text #10

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.4286. Min Act: -0.0000

Data Index: 1572637 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.2897. Min Act: -0.0000

Data Index: 1501741 (Python Code)

Max Activating Token Index: 680

Text #12

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.3936. Min Act: -0.0000

Data Index: 1585979 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.2229. Min Act: -0.0000

Data Index: 1578109 (Python Code)

Max Activating Token Index: 665

Text #14

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.5162. Min Act: -0.0000

Data Index: 1468558 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.2740. Min Act: -0.0000

Data Index: 1364635 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.1212. Min Act: -0.0000

Data Index: 1361072 (Python Code)

Max Activating Token Index: 749

Text #17

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.0922. Min Act: -0.0000

Data Index: 1418917 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.3845. Min Act: -0.0000

Data Index: 1603351 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 4.2354. Min Range: -4.2354

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1514314 (Python Code)

Max Activating Token Index: 113