Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 354 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0331. Min Act: 0.0000

Data Index: 1628371 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1594465 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1527768 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1389590 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1437567 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1365012 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1583604 (Python Code)

Max Activating Token Index: 579

Text #7

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1578241 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1593127 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1511454 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1570236 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1393784 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1460369 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8102. Min Act: 0.0000

Data Index: 1632960 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1391136 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1435639 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7514. Min Act: -0.0001

Data Index: 1615081 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7826. Min Act: -0.0001

Data Index: 1443970 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1475745 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7060. Min Act: -0.0001

Data Index: 1652055 (Python Code)

Max Activating Token Index: 103