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

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

Neuron 487 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0475. Min Range: -1.0475

Max Act: 1.0475. Min Act: -0.0000

Data Index: 742791 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9241. Min Act: -0.0000

Data Index: 172196 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1610501 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1328325 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8543. Min Act: -0.0000

Data Index: 984709 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1328274 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1647327 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8023. Min Act: -0.0000

Data Index: 990261 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9455. Min Act: -0.0000

Data Index: 614056 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1612064 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8827. Min Act: -0.0000

Data Index: 446362 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8583. Min Act: -0.0000

Data Index: 849113 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1327650 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1478997 (Python Code)

Max Activating Token Index: 789

Text #14

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8774. Min Act: -0.0000

Data Index: 459830 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1413955 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.9032. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1407620 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1492251 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 1.0475. Min Range: -1.0475

Max Act: 0.7869. Min Act: -0.0000

Data Index: 742496 (C4 (Web Text))

Max Activating Token Index: 798