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

Dataset: The Pile

Neuron 1563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0000

Data Index: 94736 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5894. Min Act: -0.0000

Data Index: 619439 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1754093 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1719016 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1917715 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6028. Min Act: -0.0000

Data Index: 23436 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5007. Min Act: -0.0000

Data Index: 233761 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5080. Min Act: -0.0000

Data Index: 573952 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4899. Min Act: -0.0000

Data Index: 861187 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1711757 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1950251 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1559956 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1715208 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1946781 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4781. Min Act: -0.0000

Data Index: 833990 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4152. Min Act: -0.0000

Data Index: 799433 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4225. Min Act: -0.0000

Data Index: 300508 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4405. Min Act: -0.0000

Data Index: 654306 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4162. Min Act: -0.0000

Data Index: 784728 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4201. Min Act: -0.0000

Data Index: 767091 (The Pile)

Max Activating Token Index: 281