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

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

Neuron 165 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: 0.9790. Min Range: -0.9790

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1620358 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1551216 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1434944 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1379519 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8231. Min Act: -0.0000

Data Index: 431106 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1586314 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1370891 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7877. Min Act: -0.0000

Data Index: 37809 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1584228 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1398164 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1436402 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1429226 (Python Code)

Max Activating Token Index: 869

Text #12

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1497756 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1048717 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1623760 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1515995 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1460002 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1035258 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7048. Min Act: 0.0000

Data Index: 1336808 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1511920 (Python Code)

Max Activating Token Index: 798