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

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

Neuron 4459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1508965 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1578016 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1536302 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1436888 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1395196 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1513294 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1393082 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1451368 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1402079 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1526383 (Python Code)

Max Activating Token Index: 95

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1438215 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1643025 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1565040 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1579756 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1527714 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1635715 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1378595 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7310. Min Act: -0.0001

Data Index: 1655749 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1452006 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1455517 (Python Code)

Max Activating Token Index: 117