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

Dataset: The Pile

Neuron 2752 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1720317 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2670. Min Act: -0.0000

Data Index: 208184 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1190891 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1868790 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2764. Min Act: -0.0000

Data Index: 334598 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1970635 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2224. Min Act: -0.0000

Data Index: 831091 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1535570 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2323. Min Act: -0.0000

Data Index: 391591 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1635544 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1190361 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1407710 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2164. Min Act: -0.0000

Data Index: 512726 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1193335 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1939781 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1313438 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1278364 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2019. Min Act: -0.0000

Data Index: 701688 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1851. Min Act: -0.0000

Data Index: 569575 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2044. Min Act: -0.0000

Data Index: 415285 (The Pile)

Max Activating Token Index: 680