Model: None

Dataset: The Pile

Neuron 795 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.1109. Min Act: -0.1700

Data Index: 3428090 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7982. Min Act: -0.1700

Data Index: 8645920 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7982. Min Act: -0.1700

Data Index: 4322671 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7825. Min Act: -0.1700

Data Index: 10627168 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7512. Min Act: -0.1700

Data Index: 1147882 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7356. Min Act: -0.1700

Data Index: 10576083 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7356. Min Act: -0.1700

Data Index: 2624552 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7200. Min Act: -0.1700

Data Index: 5172126 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.7043. Min Act: -0.1700

Data Index: 1708841 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6730. Min Act: -0.1700

Data Index: 10196559 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6730. Min Act: -0.1700

Data Index: 7916480 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6574. Min Act: -0.1700

Data Index: 9325329 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6574. Min Act: -0.1700

Data Index: 659118 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6574. Min Act: -0.1700

Data Index: 9364164 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6574. Min Act: -0.1700

Data Index: 9486876 (The Pile)

Max Activating Token Index: 933

Text #15

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6417. Min Act: -0.1700

Data Index: 4162740 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6261. Min Act: -0.1700

Data Index: 6999081 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6261. Min Act: -0.1700

Data Index: 2935591 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6261. Min Act: -0.1700

Data Index: 2608000 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.6104. Min Act: -0.1700

Data Index: 4492533 (The Pile)

Max Activating Token Index: 783