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

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

Neuron 5773 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7655. Min Range: -1.7655

Max Act: 1.7655. Min Act: -0.0000

Data Index: 1620970 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 1.7655. Min Range: -1.7655

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1402104 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 1.7655. Min Range: -1.7655

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1504909 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 1.7655. Min Range: -1.7655

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1488647 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1607975 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1368141 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1648746 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1437771 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1540623 (Python Code)

Max Activating Token Index: 332

Text #9

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1574047 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1422872 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1364532 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1559564 (Python Code)

Max Activating Token Index: 186

Text #13

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1532313 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1613169 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1548063 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1518831 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1567770 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1466383 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 1.7655. Min Range: -1.7655

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1421031 (Python Code)

Max Activating Token Index: 341