Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5974 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.9660. Min Act: -0.1700
Data Index: 491757 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.7160. Min Act: -0.1700
Data Index: 793192 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.5285. Min Act: -0.1700
Data Index: 5992066 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4972. Min Act: -0.1700
Data Index: 5364260 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4035. Min Act: -0.1700
Data Index: 1753656 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3410. Min Act: -0.1700
Data Index: 7234407 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3097. Min Act: -0.1700
Data Index: 2269208 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3097. Min Act: -0.1700
Data Index: 1873170 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2785. Min Act: -0.1700
Data Index: 4958350 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 4188731 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2472. Min Act: -0.1700
Data Index: 1255355 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1361039 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 6097599 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1533891 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 884573 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.1847. Min Act: -0.1700
Data Index: 6188303 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.1847. Min Act: -0.1700
Data Index: 1874126 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.1847. Min Act: -0.1700
Data Index: 5211086 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.1535. Min Act: -0.1700
Data Index: 1848522 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.1535. Min Act: -0.1700
Data Index: 7278189 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19