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

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

Neuron 4141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1557124 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0685. Min Act: -0.0000

Data Index: 1377582 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1498994 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8979. Min Act: -0.0000

Data Index: 1529854 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0812. Min Act: -0.0000

Data Index: 1465584 (Python Code)

Max Activating Token Index: 713

Text #5

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1379803 (Python Code)

Max Activating Token Index: 858

Text #6

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9012. Min Act: -0.0000

Data Index: 1360006 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1612303 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8246. Min Act: -0.0000

Data Index: 1625642 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9405. Min Act: -0.0000

Data Index: 686442 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9103. Min Act: -0.0000

Data Index: 141914 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6864. Min Act: -0.0000

Data Index: 1641881 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7578. Min Act: -0.0000

Data Index: 1453519 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7461. Min Act: -0.0000

Data Index: 1606311 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6462. Min Act: -0.0000

Data Index: 24396 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1583423 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6386. Min Act: -0.0000

Data Index: 173625 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1627668 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7808. Min Act: -0.0000

Data Index: 1066031 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6119. Min Act: -0.0000

Data Index: 537054 (C4 (Web Text))

Max Activating Token Index: 125