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

Dataset: Open Web Text

Neuron 1037 in Layer 2

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: 1.8501. Min Range: -1.8501

Max Act: 1.8501. Min Act: -0.1700

Data Index: 7802884 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8256. Min Act: -0.1700

Data Index: 5669171 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8222. Min Act: -0.1700

Data Index: 3522530 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8064. Min Act: -0.1700

Data Index: 8205267 (Open Web Text)

Max Activating Token Index: 715

Text #4

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8101. Min Act: -0.1700

Data Index: 6700612 (Open Web Text)

Max Activating Token Index: 833

Text #5

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8279. Min Act: -0.1700

Data Index: 4927517 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8244. Min Act: -0.1694

Data Index: 1182499 (Open Web Text)

Max Activating Token Index: 397

Text #7

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8126. Min Act: -0.1700

Data Index: 1256020 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8129. Min Act: -0.1700

Data Index: 2774181 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8134. Min Act: -0.1696

Data Index: 2489852 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7952. Min Act: -0.1700

Data Index: 5269622 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8017. Min Act: -0.1700

Data Index: 2867915 (Open Web Text)

Max Activating Token Index: 419

Text #12

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7999. Min Act: -0.1700

Data Index: 2774183 (Open Web Text)

Max Activating Token Index: 168

Text #13

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8023. Min Act: -0.1700

Data Index: 4696825 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8013. Min Act: -0.1696

Data Index: 7724216 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8029. Min Act: -0.1625

Data Index: 6358284 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7961. Min Act: -0.1698

Data Index: 2867914 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.7969. Min Act: -0.1700

Data Index: 5682123 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8009. Min Act: -0.1699

Data Index: 2774180 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 1.8501. Min Range: -1.8501

Max Act: 1.8002. Min Act: -0.1700

Data Index: 5896172 (Open Web Text)

Max Activating Token Index: 922