Model: None

Dataset: The Pile

Neuron 870 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')

Text #0

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.1016. Min Act: -0.1700

Data Index: 6203823 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 1733857 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 5741567 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 10175462 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0227. Min Act: -0.1700

Data Index: 6620724 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0069. Min Act: -0.1700

Data Index: 6657524 (The Pile)

Max Activating Token Index: 306

Text #6

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9910. Min Act: -0.1700

Data Index: 5825519 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9594. Min Act: -0.1700

Data Index: 2823253 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9436. Min Act: -0.1700

Data Index: 8763369 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9436. Min Act: -0.1700

Data Index: 8061556 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9436. Min Act: -0.1700

Data Index: 9168332 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9436. Min Act: -0.1700

Data Index: 2042560 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9277. Min Act: -0.1700

Data Index: 4047958 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9119. Min Act: -0.1700

Data Index: 1252573 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9119. Min Act: -0.1700

Data Index: 584330 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9119. Min Act: -0.1700

Data Index: 8867836 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9119. Min Act: -0.1700

Data Index: 9987575 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9119. Min Act: -0.1700

Data Index: 1964661 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.8960. Min Act: -0.1700

Data Index: 2913269 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.8960. Min Act: -0.1700

Data Index: 5131512 (The Pile)

Max Activating Token Index: 102