Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1660 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.9666. Min Act: -0.1700
Data Index: 8592195 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.5916. Min Act: -0.1700
Data Index: 1775875 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.3729. Min Act: -0.1700
Data Index: 3385159 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.3729. Min Act: -0.1700
Data Index: 2537286 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.2166. Min Act: -0.1700
Data Index: 2562179 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.1541. Min Act: -0.1700
Data Index: 6103131 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.0604. Min Act: -0.1700
Data Index: 1182853 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.0291. Min Act: -0.1700
Data Index: 923003 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9979. Min Act: -0.1700
Data Index: 8106969 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 5373306 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7680949 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 7816465 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2778407 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 849506 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 8326064 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4329223 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9354. Min Act: -0.1700
Data Index: 1919679 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2031878 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2707992 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9666. Min Range: -6.9666
Max Act: 5.9041. Min Act: -0.1700
Data Index: 3111589 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19