Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1353 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1379134 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1587197 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1474566 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1656598 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1392719 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1604806 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1504853 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 1.0573. Min Range: -1.0573

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1366326 (Python Code)

Max Activating Token Index: 577

Text #8

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1458339 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1471118 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1638275 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1385417 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1601109 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1595294 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1543539 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1440769 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1555038 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1628483 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1601369 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 1.0573. Min Range: -1.0573

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1527416 (Python Code)

Max Activating Token Index: 1004