Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1459983 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3142. Min Act: -0.0000

Data Index: 411958 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1671956 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1960531 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1301994 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1736717 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1975898 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1831. Min Act: -0.0000

Data Index: 606344 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2168. Min Act: -0.0000

Data Index: 330610 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1983. Min Act: -0.0000

Data Index: 821497 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1151881 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1622101 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2002. Min Act: -0.0000

Data Index: 316586 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2080. Min Act: -0.0000

Data Index: 397491 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1855. Min Act: -0.0000

Data Index: 582104 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1384209 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1827. Min Act: -0.0000

Data Index: 777287 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1099976 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1948. Min Act: -0.0000

Data Index: 729373 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1112884 (The Pile)

Max Activating Token Index: 793