Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 873 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8804. Min Act: -0.1700

Data Index: 6188201 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.9109. Min Act: -0.1700

Data Index: 6257828 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8831. Min Act: -0.1700

Data Index: 2897914 (Open Web Text)

Max Activating Token Index: 539

Text #3

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1511774 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8304. Min Act: -0.1700

Data Index: 5932814 (Open Web Text)

Max Activating Token Index: 724

Text #5

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8513. Min Act: -0.1700

Data Index: 1905493 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8387. Min Act: -0.1700

Data Index: 5336015 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8251. Min Act: -0.1700

Data Index: 1806357 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8206. Min Act: -0.1700

Data Index: 2432984 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8091. Min Act: -0.1700

Data Index: 428588 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8051. Min Act: -0.1700

Data Index: 2438021 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.7870. Min Act: -0.1700

Data Index: 1370641 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8076. Min Act: -0.1700

Data Index: 1255239 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8039. Min Act: -0.1700

Data Index: 5065517 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.7870. Min Act: -0.1700

Data Index: 364804 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8034. Min Act: -0.1700

Data Index: 1329138 (Open Web Text)

Max Activating Token Index: 575

Text #16

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8027. Min Act: -0.1700

Data Index: 4604560 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.7855. Min Act: -0.1700

Data Index: 5638002 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.8078. Min Act: -0.1700

Data Index: 5721900 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 3.9109. Min Range: -3.9109

Max Act: 3.7966. Min Act: -0.1700

Data Index: 3062239 (Open Web Text)

Max Activating Token Index: 614