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

Dataset: The Pile

Neuron 1649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1049840 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.2262. Min Act: -0.0000

Data Index: 345828 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1741090 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9477. Min Act: -0.0000

Data Index: 395595 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1905741 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1316440 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8764. Min Act: -0.0000

Data Index: 517203 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1758673 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8790. Min Act: -0.0000

Data Index: 348869 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1906824 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1247461 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.2262. Min Range: -1.2262

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1658364 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9258. Min Act: -0.0000

Data Index: 613405 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1175524 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9463. Min Act: -0.0000

Data Index: 490952 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8325. Min Act: -0.0000

Data Index: 638195 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1401575 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8475. Min Act: -0.0000

Data Index: 551291 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1622880 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 1.2262. Min Range: -1.2262

Max Act: 0.8103. Min Act: -0.0000

Data Index: 683944 (The Pile)

Max Activating Token Index: 766