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

Dataset: Open Web Text

Neuron 1341 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: 3.3607. Min Range: -3.3607

Max Act: 3.3607. Min Act: -0.1700

Data Index: 5766301 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.1370. Min Act: -0.1700

Data Index: 3959004 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0987. Min Act: -0.1700

Data Index: 3737828 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.1325. Min Act: -0.1700

Data Index: 18438 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0272. Min Act: -0.1700

Data Index: 1746860 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0489. Min Act: -0.1700

Data Index: 1679656 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0227. Min Act: -0.1700

Data Index: 3283703 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0184. Min Act: -0.1700

Data Index: 1635243 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9845. Min Act: -0.1700

Data Index: 271643 (Open Web Text)

Max Activating Token Index: 787

Text #9

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0057. Min Act: -0.1700

Data Index: 5713692 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9945. Min Act: -0.1700

Data Index: 5578987 (Open Web Text)

Max Activating Token Index: 912

Text #11

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0327. Min Act: -0.1700

Data Index: 8334686 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0147. Min Act: -0.1700

Data Index: 3518352 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0078. Min Act: -0.1700

Data Index: 1144633 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9938. Min Act: -0.1700

Data Index: 1930152 (Open Web Text)

Max Activating Token Index: 836

Text #15

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9896. Min Act: -0.1700

Data Index: 6009662 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0025. Min Act: -0.1700

Data Index: 3801592 (Open Web Text)

Max Activating Token Index: 313

Text #17

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9728. Min Act: -0.1700

Data Index: 5409668 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 3.3607. Min Range: -3.3607

Max Act: 2.9735. Min Act: -0.1700

Data Index: 127060 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 3.3607. Min Range: -3.3607

Max Act: 3.0098. Min Act: -0.1700

Data Index: 4447161 (Open Web Text)

Max Activating Token Index: 532