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

Dataset: The Pile

Neuron 2115 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: 0.8738. Min Range: -0.8738

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1278646 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8006. Min Act: -0.0000

Data Index: 884403 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1047350 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1308442 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8599. Min Act: -0.0000

Data Index: 391839 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1585437 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1753140 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7844. Min Act: -0.0000

Data Index: 987687 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7657. Min Act: -0.0000

Data Index: 838948 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7522. Min Act: -0.0000

Data Index: 396166 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1176067 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1005394 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7687. Min Act: -0.0000

Data Index: 592409 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1612143 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7343. Min Act: -0.0000

Data Index: 802383 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1900663 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1633639 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1124903 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1934905 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1657429 (The Pile)

Max Activating Token Index: 949