Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.1652. Min Act: -0.1700
Data Index: 6365013 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.1027. Min Act: -0.1700
Data Index: 3750982 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.1027. Min Act: -0.1700
Data Index: 748028 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.0402. Min Act: -0.1700
Data Index: 195363 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.0402. Min Act: -0.1700
Data Index: 7577904 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.0089. Min Act: -0.1700
Data Index: 2354741 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1652. Min Range: -4.1652
Max Act: 4.0089. Min Act: -0.1700
Data Index: 7843280 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9777. Min Act: -0.1700
Data Index: 4224548 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9151. Min Act: -0.1700
Data Index: 4224556 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9151. Min Act: -0.1700
Data Index: 7577902 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9151. Min Act: -0.1700
Data Index: 4224559 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9151. Min Act: -0.1700
Data Index: 7074445 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.9464. Min Act: -0.1700
Data Index: 6721137 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8839. Min Act: -0.1700
Data Index: 4224553 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8839. Min Act: -0.1700
Data Index: 8351019 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8839. Min Act: -0.1700
Data Index: 3032056 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8526. Min Act: -0.1700
Data Index: 7795730 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8526. Min Act: -0.1700
Data Index: 1337487 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8839. Min Act: -0.1700
Data Index: 5332990 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1652. Min Range: -4.1652
Max Act: 3.8839. Min Act: -0.1700
Data Index: 4612759 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19