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

Dataset: Open Web Text

Neuron 979 in Layer 3

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: 2.1170. Min Range: -2.1170

Max Act: 2.1170. Min Act: -0.1700

Data Index: 8680594 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 2.1170. Min Range: -2.1170

Max Act: 2.0301. Min Act: -0.1700

Data Index: 7401763 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 2.1170. Min Range: -2.1170

Max Act: 2.0258. Min Act: -0.1700

Data Index: 1857139 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.9899. Min Act: -0.1700

Data Index: 8456663 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.9106. Min Act: -0.1700

Data Index: 6913237 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.8939. Min Act: -0.1700

Data Index: 2594237 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.8052. Min Act: -0.1700

Data Index: 4809841 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.8306. Min Act: -0.1700

Data Index: 2252748 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7745. Min Act: -0.1700

Data Index: 5505754 (Open Web Text)

Max Activating Token Index: 918

Text #9

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7155. Min Act: -0.1700

Data Index: 8036285 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7062. Min Act: -0.1700

Data Index: 8676416 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7886. Min Act: -0.1700

Data Index: 1183191 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7861. Min Act: -0.1700

Data Index: 8201140 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7642. Min Act: -0.1700

Data Index: 5017102 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7327. Min Act: -0.1700

Data Index: 3790508 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7309. Min Act: -0.1700

Data Index: 13854 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.8030. Min Act: -0.1700

Data Index: 1005332 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.6860. Min Act: -0.1700

Data Index: 213405 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.6785. Min Act: -0.1700

Data Index: 336299 (Open Web Text)

Max Activating Token Index: 409

Text #19

Max Range: 2.1170. Min Range: -2.1170

Max Act: 1.7593. Min Act: -0.1700

Data Index: 4863822 (Open Web Text)

Max Activating Token Index: 116