Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.3267. Min Act: -0.1700
Data Index: 4814331 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.2642. Min Act: -0.1700
Data Index: 6996474 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.2954. Min Act: -0.1700
Data Index: 3659516 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.3267. Min Act: -0.1700
Data Index: 3755764 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.2642. Min Act: -0.1700
Data Index: 5696698 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.2642. Min Act: -0.1700
Data Index: 3200020 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.1392. Min Act: -0.1700
Data Index: 7831927 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.0767. Min Act: -0.1700
Data Index: 2581534 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.0454. Min Act: -0.1700
Data Index: 62719 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.0142. Min Act: -0.1700
Data Index: 4839947 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.0454. Min Act: -0.1700
Data Index: 8162585 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3267. Min Range: -7.3267
Max Act: 7.0142. Min Act: -0.1700
Data Index: 131922 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9829. Min Act: -0.1700
Data Index: 1354882 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9829. Min Act: -0.1700
Data Index: 2143684 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9829. Min Act: -0.1700
Data Index: 3641665 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9829. Min Act: -0.1700
Data Index: 7984008 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9517. Min Act: -0.1700
Data Index: 3889920 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9204. Min Act: -0.1700
Data Index: 4285905 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.9204. Min Act: -0.1700
Data Index: 3978913 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3267. Min Range: -7.3267
Max Act: 6.8892. Min Act: -0.1700
Data Index: 742762 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19