Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3668. Min Range: -4.3668
Max Act: 4.3668. Min Act: -0.1700
Data Index: 8503760 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.9292. Min Act: -0.1700
Data Index: 7211166 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.9292. Min Act: -0.1700
Data Index: 1678519 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.9292. Min Act: -0.1700
Data Index: 4212839 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1898691 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8979. Min Act: -0.1700
Data Index: 4212837 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8667. Min Act: -0.1700
Data Index: 8462615 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8041. Min Act: -0.1700
Data Index: 1377785 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8041. Min Act: -0.1700
Data Index: 1144656 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.8041. Min Act: -0.1700
Data Index: 7866282 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7728. Min Act: -0.1700
Data Index: 1466773 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7728. Min Act: -0.1700
Data Index: 4803945 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4180820 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7416. Min Act: -0.1700
Data Index: 8799523 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7103. Min Act: -0.1700
Data Index: 2706866 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7103. Min Act: -0.1700
Data Index: 5429028 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7103. Min Act: -0.1700
Data Index: 7862574 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.7103. Min Act: -0.1700
Data Index: 6407424 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.6790. Min Act: -0.1700
Data Index: 2952871 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3668. Min Range: -4.3668
Max Act: 3.6790. Min Act: -0.1700
Data Index: 7522339 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19