Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.2924. Min Act: -0.1700
Data Index: 8828867 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.1362. Min Act: -0.1700
Data Index: 3474400 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.1049. Min Act: -0.1700
Data Index: 4605668 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0736. Min Act: -0.1700
Data Index: 3090555 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.1049. Min Act: -0.1700
Data Index: 624807 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0424. Min Act: -0.1700
Data Index: 5307898 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0111. Min Act: -0.1700
Data Index: 6084465 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0111. Min Act: -0.1700
Data Index: 2777524 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0111. Min Act: -0.1700
Data Index: 8538462 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0424. Min Act: -0.1700
Data Index: 324096 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 4026233 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2924. Min Range: -4.2924
Max Act: 4.0111. Min Act: -0.1700
Data Index: 6530966 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 4374877 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 7624415 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 568371 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 4161876 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9799. Min Act: -0.1700
Data Index: 3425564 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9486. Min Act: -0.1700
Data Index: 1825048 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9486. Min Act: -0.1700
Data Index: 7560193 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2924. Min Range: -4.2924
Max Act: 3.9486. Min Act: -0.1700
Data Index: 3440747 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19