Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.7814. Min Act: -0.1700
Data Index: 4074849 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.5626. Min Act: -0.1700
Data Index: 5896647 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.5001. Min Act: -0.1700
Data Index: 5580645 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.5001. Min Act: -0.1700
Data Index: 7001620 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.4376. Min Act: -0.1700
Data Index: 4006406 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.4064. Min Act: -0.1700
Data Index: 1796588 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.4064. Min Act: -0.1700
Data Index: 229323 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.4064. Min Act: -0.1700
Data Index: 6239368 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.3439. Min Act: -0.1700
Data Index: 972304 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 7184235 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 4559484 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 4559485 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 7590907 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 2219649 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2501. Min Act: -0.1700
Data Index: 2356536 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2501. Min Act: -0.1700
Data Index: 4121569 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2189. Min Act: -0.1700
Data Index: 4270999 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2189. Min Act: -0.1700
Data Index: 1252731 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2189. Min Act: -0.1700
Data Index: 850627 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7814. Min Range: -5.7814
Max Act: 5.2189. Min Act: -0.1700
Data Index: 486197 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19