Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.8869. Min Act: -0.1700
Data Index: 5692392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.7618. Min Act: -0.1700
Data Index: 4716234 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.5897. Min Act: -0.1700
Data Index: 4566470 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.5584. Min Act: -0.1700
Data Index: 3608116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.5740. Min Act: -0.1700
Data Index: 5606964 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.5427. Min Act: -0.1700
Data Index: 4075350 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.4801. Min Act: -0.1700
Data Index: 6795670 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3860. Min Act: -0.1700
Data Index: 3189479 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.4017. Min Act: -0.1700
Data Index: 4158386 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3547. Min Act: -0.1700
Data Index: 2686693 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3703. Min Act: -0.1700
Data Index: 1010878 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3547. Min Act: -0.1700
Data Index: 3094890 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3390. Min Act: -0.1700
Data Index: 1461063 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3233. Min Act: -0.1700
Data Index: 3869355 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3076. Min Act: -0.1700
Data Index: 5036451 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3703. Min Act: -0.1700
Data Index: 2223615 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3076. Min Act: -0.1700
Data Index: 5535204 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.3233. Min Act: -0.1700
Data Index: 2841298 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.2919. Min Act: -0.1700
Data Index: 7336921 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8869. Min Range: -3.8869
Max Act: 3.2919. Min Act: -0.1700
Data Index: 2852866 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19