Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1706098 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2290. Min Act: -0.0000

Data Index: 109095 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2148. Min Act: -0.0000

Data Index: 911548 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2046. Min Act: -0.0000

Data Index: 598210 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2092. Min Act: -0.0000

Data Index: 815360 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2035. Min Act: -0.0000

Data Index: 926430 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2126. Min Act: -0.0000

Data Index: 394213 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2045. Min Act: -0.0000

Data Index: 139712 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1136595 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2056. Min Act: -0.0000

Data Index: 621273 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1935. Min Act: -0.0000

Data Index: 678244 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1144903 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1879. Min Act: -0.0000

Data Index: 270053 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1849384 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1185475 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1832. Min Act: -0.0000

Data Index: 939103 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1414859 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1860. Min Act: -0.0000

Data Index: 546115 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1994. Min Act: -0.0000

Data Index: 352707 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1733650 (The Pile)

Max Activating Token Index: 994