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

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

Neuron 5420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1905. Min Range: -4.1905

Max Act: 4.1905. Min Act: -0.0000

Data Index: 1397249 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.9606. Min Act: -0.0000

Data Index: 1362056 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.8324. Min Act: -0.0000

Data Index: 1506109 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.7915. Min Act: -0.0000

Data Index: 1362691 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.7927. Min Act: -0.0000

Data Index: 1453149 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.9233. Min Act: -0.0000

Data Index: 1584558 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.5563. Min Act: -0.0000

Data Index: 1377801 (Python Code)

Max Activating Token Index: 765

Text #7

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1360199 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.6660. Min Act: -0.0000

Data Index: 1401887 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.6502. Min Act: -0.0000

Data Index: 1604177 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.5960. Min Act: -0.0000

Data Index: 1468383 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.7256. Min Act: -0.0000

Data Index: 1562952 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.3931. Min Act: -0.0000

Data Index: 1397086 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.4846. Min Act: -0.0000

Data Index: 1602971 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.5965. Min Act: -0.0000

Data Index: 1414081 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.4311. Min Act: -0.0000

Data Index: 1592173 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.2616. Min Act: -0.0000

Data Index: 1429441 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.5333. Min Act: -0.0000

Data Index: 1391500 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.2207. Min Act: -0.0000

Data Index: 1536732 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 4.1905. Min Range: -4.1905

Max Act: 3.1515. Min Act: -0.0000

Data Index: 1389946 (Python Code)

Max Activating Token Index: 144