Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1767 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1582979 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1391868 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2070. Min Act: -0.0000

Data Index: 264809 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1149485 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2185. Min Act: 0.0000

Data Index: 846838 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1910. Min Act: -0.0000

Data Index: 560562 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2176. Min Act: -0.0000

Data Index: 618374 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1155034 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1996. Min Act: -0.0000

Data Index: 42517 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1902. Min Act: 0.0000

Data Index: 622634 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2059. Min Act: -0.0000

Data Index: 22618 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1566904 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1747225 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1959. Min Act: 0.0000

Data Index: 800832 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1902. Min Act: -0.0000

Data Index: 27190 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1867. Min Act: -0.0000

Data Index: 617948 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1035179 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1757. Min Act: 0.0000

Data Index: 174959 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1868. Min Act: -0.0000

Data Index: 865524 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1717900 (The Pile)

Max Activating Token Index: 449