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

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

Neuron 581 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4731. Min Range: -3.4731

Max Act: 3.4731. Min Act: -0.0000

Data Index: 1507734 (Python Code)

Max Activating Token Index: 135

Text #1

Max Range: 3.4731. Min Range: -3.4731

Max Act: 3.0486. Min Act: -0.0000

Data Index: 1437488 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.8917. Min Act: -0.0000

Data Index: 1560660 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.9162. Min Act: -0.0000

Data Index: 1480928 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.8766. Min Act: -0.0000

Data Index: 1460898 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.3437. Min Act: -0.0000

Data Index: 1491474 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.2479. Min Act: -0.0000

Data Index: 1382503 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.0879. Min Act: -0.0000

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1446330 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.8599. Min Act: -0.0000

Data Index: 1559317 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.1664. Min Act: -0.0000

Data Index: 1390356 (Python Code)

Max Activating Token Index: 278

Text #11

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.9021. Min Act: -0.0000

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 3.4731. Min Range: -3.4731

Max Act: 2.2172. Min Act: -0.0000

Data Index: 1392268 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1542162 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1363986 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.8608. Min Act: -0.0000

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.8453. Min Act: -0.0000

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.7299. Min Act: -0.0000

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.9111. Min Act: -0.0000

Data Index: 1618199 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 3.4731. Min Range: -3.4731

Max Act: 1.8077. Min Act: -0.0000

Data Index: 115109 (C4 (Web Text))

Max Activating Token Index: 189