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

Dataset: Open Web Text

Neuron 2859 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: 3.1458. Min Range: -3.1458

Max Act: 3.1458. Min Act: -0.1700

Data Index: 660417 (Open Web Text)

Max Activating Token Index: 675

Text #1

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0829. Min Act: -0.1700

Data Index: 7270896 (Open Web Text)

Max Activating Token Index: 321

Text #2

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0717. Min Act: -0.1700

Data Index: 3694619 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0427. Min Act: -0.1700

Data Index: 1082939 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0433. Min Act: -0.1700

Data Index: 6333110 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0436. Min Act: -0.1700

Data Index: 8072228 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0492. Min Act: -0.1700

Data Index: 7437489 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0095. Min Act: -0.1700

Data Index: 3968891 (Open Web Text)

Max Activating Token Index: 659

Text #8

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0122. Min Act: -0.1700

Data Index: 4668301 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0184. Min Act: -0.1700

Data Index: 5184725 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0033. Min Act: -0.1700

Data Index: 7381237 (Open Web Text)

Max Activating Token Index: 912

Text #11

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0275. Min Act: -0.1700

Data Index: 4535953 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0026. Min Act: -0.1700

Data Index: 5439635 (Open Web Text)

Max Activating Token Index: 339

Text #13

Max Range: 3.1458. Min Range: -3.1458

Max Act: 3.0014. Min Act: -0.1700

Data Index: 1915987 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9859. Min Act: -0.1700

Data Index: 1309364 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9821. Min Act: -0.1700

Data Index: 7042743 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9790. Min Act: -0.1700

Data Index: 5808252 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9464. Min Act: -0.1700

Data Index: 255068 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9882. Min Act: -0.1700

Data Index: 6853940 (Open Web Text)

Max Activating Token Index: 901

Text #19

Max Range: 3.1458. Min Range: -3.1458

Max Act: 2.9719. Min Act: -0.1700

Data Index: 3269129 (Open Web Text)

Max Activating Token Index: 314