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

Dataset: Open Web Text

Neuron 1919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.1109. Min Act: -0.1700

Data Index: 5867100 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0613. Min Act: -0.1700

Data Index: 2957704 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0564. Min Act: -0.1700

Data Index: 8671124 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0235. Min Act: -0.1700

Data Index: 493975 (Open Web Text)

Max Activating Token Index: 546

Text #4

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0183. Min Act: -0.1700

Data Index: 8714671 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9874. Min Act: -0.1700

Data Index: 8274197 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9740. Min Act: -0.1700

Data Index: 4965425 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9755. Min Act: -0.1700

Data Index: 3664423 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9493. Min Act: -0.1700

Data Index: 4894948 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9346. Min Act: -0.1700

Data Index: 5629053 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9130. Min Act: -0.1700

Data Index: 6805525 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8814. Min Act: -0.1700

Data Index: 6554454 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8927. Min Act: -0.1700

Data Index: 56479 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9081. Min Act: -0.1700

Data Index: 2103873 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9270. Min Act: -0.1700

Data Index: 4914244 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9282. Min Act: -0.1700

Data Index: 5498809 (Open Web Text)

Max Activating Token Index: 833

Text #16

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9209. Min Act: -0.1700

Data Index: 4033962 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8778. Min Act: -0.1700

Data Index: 6540580 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8632. Min Act: -0.1700

Data Index: 291186 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.8884. Min Act: -0.1700

Data Index: 6684728 (Open Web Text)

Max Activating Token Index: 963