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

Dataset: Open Web Text

Neuron 2716 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: 3.0840. Min Range: -3.0840

Max Act: 3.0840. Min Act: -0.1700

Data Index: 6080912 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9855. Min Act: -0.1700

Data Index: 4071111 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 3.0840. Min Range: -3.0840

Max Act: 3.0110. Min Act: -0.1700

Data Index: 4044793 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9851. Min Act: -0.1700

Data Index: 1254252 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9682. Min Act: -0.1700

Data Index: 3309614 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9409. Min Act: -0.1700

Data Index: 3746314 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9324. Min Act: -0.1700

Data Index: 5957070 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9365. Min Act: -0.1700

Data Index: 4747853 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9107. Min Act: -0.1700

Data Index: 4630376 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9211. Min Act: -0.1700

Data Index: 7297822 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8966. Min Act: -0.1700

Data Index: 5953299 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8984. Min Act: -0.1700

Data Index: 1620965 (Open Web Text)

Max Activating Token Index: 341

Text #12

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8842. Min Act: -0.1700

Data Index: 5207796 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8959. Min Act: -0.1700

Data Index: 3096356 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8780. Min Act: -0.1700

Data Index: 2050808 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9012. Min Act: -0.1700

Data Index: 8738019 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8994. Min Act: -0.1700

Data Index: 7409009 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8733. Min Act: -0.1700

Data Index: 8627203 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.9028. Min Act: -0.1700

Data Index: 4486751 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 3.0840. Min Range: -3.0840

Max Act: 2.8589. Min Act: -0.1700

Data Index: 6298473 (Open Web Text)

Max Activating Token Index: 242