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

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

Neuron 3340 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1455450 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1416699 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1492351 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1556123 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1492275 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1587657 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1538562 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1369586 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1367550 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1438154 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1363969 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1549673 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1482054 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1585473 (Python Code)

Max Activating Token Index: 275

Text #14

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1590015 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1561433 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1387266 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1453353 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1442406 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1544913 (Python Code)

Max Activating Token Index: 86