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

Dataset: Open Web Text

Neuron 727 in Layer 4

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: 1.7628. Min Range: -1.7628

Max Act: 1.7504. Min Act: -0.1700

Data Index: 7609808 (Open Web Text)

Max Activating Token Index: 904

Text #1

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7628. Min Act: -0.1700

Data Index: 5291145 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7155. Min Act: -0.1700

Data Index: 3699798 (Open Web Text)

Max Activating Token Index: 173

Text #3

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7169. Min Act: -0.1700

Data Index: 553839 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7208. Min Act: -0.1700

Data Index: 5739215 (Open Web Text)

Max Activating Token Index: 835

Text #5

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7016. Min Act: -0.1700

Data Index: 5375047 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6861. Min Act: -0.1700

Data Index: 5141390 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7088. Min Act: -0.1700

Data Index: 3700218 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.7015. Min Act: -0.1700

Data Index: 1328382 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6731. Min Act: -0.1700

Data Index: 4907986 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6786. Min Act: -0.1700

Data Index: 462740 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6851. Min Act: -0.1700

Data Index: 2528693 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6765. Min Act: -0.1700

Data Index: 4053539 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6784. Min Act: -0.1700

Data Index: 6380840 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6673. Min Act: -0.1700

Data Index: 4850676 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6531. Min Act: -0.1700

Data Index: 894244 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6724. Min Act: -0.1700

Data Index: 5257684 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6719. Min Act: -0.1700

Data Index: 5833652 (Open Web Text)

Max Activating Token Index: 774

Text #18

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6548. Min Act: -0.1700

Data Index: 1335196 (Open Web Text)

Max Activating Token Index: 774

Text #19

Max Range: 1.7628. Min Range: -1.7628

Max Act: 1.6715. Min Act: -0.1700

Data Index: 1339151 (Open Web Text)

Max Activating Token Index: 481