Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.7217. Min Act: -0.1700
Data Index: 8033503 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.6592. Min Act: -0.1700
Data Index: 4289301 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.6280. Min Act: -0.1700
Data Index: 8125326 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5967. Min Act: -0.1700
Data Index: 1614707 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5967. Min Act: -0.1700
Data Index: 3473619 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5967. Min Act: -0.1700
Data Index: 5186900 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5655. Min Act: -0.1700
Data Index: 2246666 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5655. Min Act: -0.1700
Data Index: 1990883 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 4749834 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 3326564 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 2506545 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 8318165 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 5533823 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5342. Min Act: -0.1700
Data Index: 815418 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 4320223 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 7558044 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 7206710 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 6533365 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5960741 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7217. Min Range: -4.7217
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5361060 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19