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

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

Neuron 5066 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: 4.5985. Min Range: -4.5985

Max Act: 4.5985. Min Act: -0.0000

Data Index: 1630130 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.4689. Min Act: -0.0000

Data Index: 1591093 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.1099. Min Act: -0.0000

Data Index: 1523491 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.4568. Min Act: -0.0000

Data Index: 1450873 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.0431. Min Act: -0.0000

Data Index: 1434803 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.2104. Min Act: -0.0000

Data Index: 1544333 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.3923. Min Act: -0.0000

Data Index: 1560977 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.0385. Min Act: -0.0000

Data Index: 1363851 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.8860. Min Act: -0.0000

Data Index: 1649436 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.9880. Min Act: -0.0000

Data Index: 1593695 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.1253. Min Act: -0.0000

Data Index: 1462479 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.7270. Min Act: -0.0000

Data Index: 1529466 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.8560. Min Act: -0.0000

Data Index: 1534863 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.8205. Min Act: -0.0000

Data Index: 1470164 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.6358. Min Act: -0.0000

Data Index: 1584717 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.8106. Min Act: -0.0000

Data Index: 1567976 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.6216. Min Act: -0.0000

Data Index: 1448353 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.7140. Min Act: -0.0000

Data Index: 1519598 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 4.5985. Min Range: -4.5985

Max Act: 4.0725. Min Act: -0.0000

Data Index: 1419798 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 4.5985. Min Range: -4.5985

Max Act: 3.5783. Min Act: -0.0000

Data Index: 1461185 (Python Code)

Max Activating Token Index: 813