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

Dataset: Open Web Text

Neuron 2084 in Layer 1

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: 1.7664. Min Range: -1.7664

Max Act: 1.7613. Min Act: -0.1700

Data Index: 44797 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7664. Min Act: -0.1700

Data Index: 2600497 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7447. Min Act: -0.1700

Data Index: 6019890 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7399. Min Act: -0.1700

Data Index: 5261468 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7351. Min Act: -0.1700

Data Index: 2025923 (Open Web Text)

Max Activating Token Index: 633

Text #5

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7176. Min Act: -0.1700

Data Index: 480313 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7202. Min Act: -0.1700

Data Index: 6365471 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7248. Min Act: -0.1700

Data Index: 7777711 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7089. Min Act: -0.1700

Data Index: 6017635 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7049. Min Act: -0.1700

Data Index: 2878674 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7141. Min Act: -0.1700

Data Index: 1088985 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.7028. Min Act: -0.1700

Data Index: 3716724 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6920. Min Act: -0.1700

Data Index: 7909938 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6944. Min Act: -0.1700

Data Index: 6635745 (Open Web Text)

Max Activating Token Index: 129

Text #14

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6915. Min Act: -0.1700

Data Index: 453667 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6861. Min Act: -0.1700

Data Index: 4423611 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6985. Min Act: -0.1700

Data Index: 1532082 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6933. Min Act: -0.1700

Data Index: 7948206 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6884. Min Act: -0.1700

Data Index: 6152012 (Open Web Text)

Max Activating Token Index: 945

Text #19

Max Range: 1.7664. Min Range: -1.7664

Max Act: 1.6850. Min Act: -0.1700

Data Index: 4616669 (Open Web Text)

Max Activating Token Index: 158