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

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

Neuron 3265 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: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1441861 (Python Code)

Max Activating Token Index: 444

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1628525 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1560141 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1642276 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1613269 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1656563 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1459619 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1393781 (Python Code)

Max Activating Token Index: 148

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1627058 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1375575 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1463222 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1503821 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1614527 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2591. Min Act: -0.0000

Data Index: 536960 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1400565 (Python Code)

Max Activating Token Index: 469

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1554229 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1394653 (Python Code)

Max Activating Token Index: 640

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1482981 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1460881 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1504018 (Python Code)

Max Activating Token Index: 459