Model: None

Dataset: The Pile

Neuron 3520 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: 3.1109. Min Range: -3.1109

Max Act: 3.1109. Min Act: -0.1700

Data Index: 1062073 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0636. Min Act: -0.1700

Data Index: 2101481 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0004. Min Act: -0.1700

Data Index: 3137600 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9213. Min Act: -0.1700

Data Index: 3102718 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9054. Min Act: -0.1700

Data Index: 10391748 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8737. Min Act: -0.1700

Data Index: 9664088 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8737. Min Act: -0.1700

Data Index: 9130158 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8578. Min Act: -0.1700

Data Index: 6517269 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8578. Min Act: -0.1700

Data Index: 4061394 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8419. Min Act: -0.1700

Data Index: 10360195 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8260. Min Act: -0.1700

Data Index: 9029202 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8260. Min Act: -0.1700

Data Index: 9859556 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8101. Min Act: -0.1700

Data Index: 4471273 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7942. Min Act: -0.1700

Data Index: 7142514 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7942. Min Act: -0.1700

Data Index: 8470720 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7942. Min Act: -0.1700

Data Index: 5634269 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7783. Min Act: -0.1700

Data Index: 6406656 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7783. Min Act: -0.1700

Data Index: 8396801 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7783. Min Act: -0.1700

Data Index: 8924047 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.7783. Min Act: -0.1699

Data Index: 777689 (The Pile)

Max Activating Token Index: 177