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

Dataset: The Pile

Neuron 4815 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: 1.4755. Min Range: -1.4755

Max Act: 1.4755. Min Act: -0.0000

Data Index: 958811 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2681. Min Act: -0.0000

Data Index: 604279 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1341435 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1523. Min Act: -0.0000

Data Index: 970196 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0739. Min Act: -0.0000

Data Index: 380341 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1082. Min Act: -0.0000

Data Index: 200049 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0940. Min Act: -0.0000

Data Index: 119955 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0369. Min Act: -0.0000

Data Index: 195899 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0713. Min Act: 0.0000

Data Index: 475714 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1461184 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.0401. Min Act: -0.0000

Data Index: 342122 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1315174 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1218471 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.8974. Min Act: -0.0000

Data Index: 721703 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1178873 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1029902 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.9169. Min Act: -0.0000

Data Index: 157647 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1022629 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1472929 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 1.4755. Min Range: -1.4755

Max Act: 0.9412. Min Act: -0.0000

Data Index: 131273 (The Pile)

Max Activating Token Index: 643