Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4384 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0949. Min Range: -7.0949
Max Act: 7.0949. Min Act: -0.1700
Data Index: 6717629 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0949. Min Range: -7.0949
Max Act: 7.0012. Min Act: -0.1700
Data Index: 8362806 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.9074. Min Act: -0.1700
Data Index: 4999725 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.8137. Min Act: -0.1700
Data Index: 5836130 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.7824. Min Act: -0.1700
Data Index: 8199639 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.7199. Min Act: -0.1700
Data Index: 6383435 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.6574. Min Act: -0.1700
Data Index: 631371 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.6887. Min Act: -0.1700
Data Index: 6922027 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.6574. Min Act: -0.1700
Data Index: 1043225 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.6574. Min Act: -0.1700
Data Index: 4344424 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.6262. Min Act: -0.1700
Data Index: 1104598 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 5658675 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 6164957 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 2805797 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 6783936 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5637. Min Act: -0.1700
Data Index: 5063794 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 3617247 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5637. Min Act: -0.1700
Data Index: 1810153 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5324. Min Act: -0.1700
Data Index: 2962091 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0949. Min Range: -7.0949
Max Act: 6.5324. Min Act: -0.1700
Data Index: 303911 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19