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

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

Neuron 517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2739. Min Act: -0.0002

Data Index: 1567927 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2351. Min Act: -0.0002

Data Index: 1435164 (Python Code)

Max Activating Token Index: 236

Text #2

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2127. Min Act: -0.0002

Data Index: 1444290 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2103. Min Act: -0.0002

Data Index: 1376385 (Python Code)

Max Activating Token Index: 928

Text #4

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2066. Min Act: -0.0002

Data Index: 1486316 (Python Code)

Max Activating Token Index: 369

Text #5

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2026. Min Act: -0.0002

Data Index: 1602177 (Python Code)

Max Activating Token Index: 418

Text #6

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1997. Min Act: -0.0002

Data Index: 1556026 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1961. Min Act: -0.0002

Data Index: 1604456 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1949. Min Act: -0.0002

Data Index: 1432627 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1827. Min Act: -0.0002

Data Index: 1466544 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1945. Min Act: -0.0002

Data Index: 1572949 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1943. Min Act: -0.0002

Data Index: 1505043 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1850. Min Act: -0.0002

Data Index: 1564433 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1792. Min Act: -0.0002

Data Index: 1371460 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1633315 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1841. Min Act: -0.0002

Data Index: 1551297 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1789. Min Act: -0.0002

Data Index: 1602675 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1617045 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1617279 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1478095 (Python Code)

Max Activating Token Index: 806