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

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

Neuron 3964 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: 1.9325. Min Range: -1.9325

Max Act: 1.9325. Min Act: -0.0000

Data Index: 1513401 (Python Code)

Max Activating Token Index: 770

Text #1

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1609250 (Python Code)

Max Activating Token Index: 486

Text #2

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.4417. Min Act: -0.0000

Data Index: 213703 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.4927. Min Act: -0.0000

Data Index: 380309 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1479264 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1461881 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1546801 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1490503 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1621395 (Python Code)

Max Activating Token Index: 301

Text #9

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1594046 (Python Code)

Max Activating Token Index: 512

Text #10

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1550330 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1527360 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1561277 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1506474 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1416214 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1418425 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1571256 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1387. Min Act: -0.0000

Data Index: 75000 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1584. Min Act: -0.0000

Data Index: 454087 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.9325. Min Range: -1.9325

Max Act: 1.1028. Min Act: -0.0000

Data Index: 788759 (C4 (Web Text))

Max Activating Token Index: 383