Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.6816. Min Act: -0.1700
Data Index: 6801975 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.6504. Min Act: -0.1700
Data Index: 670985 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5878. Min Act: -0.1700
Data Index: 204651 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5878. Min Act: -0.1700
Data Index: 7349137 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5878. Min Act: -0.1700
Data Index: 4968534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5878. Min Act: -0.1700
Data Index: 7056923 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 6291101 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 1275634 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 3553809 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 1798902 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 8022085 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 8358074 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4938. Min Act: -0.1700
Data Index: 6549947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4938. Min Act: -0.1700
Data Index: 5900322 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4938. Min Act: -0.1700
Data Index: 8619911 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4938. Min Act: -0.1700
Data Index: 1588182 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4938. Min Act: -0.1700
Data Index: 6790561 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.5251. Min Act: -0.1700
Data Index: 6500211 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4625. Min Act: -0.1700
Data Index: 868402 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6816. Min Range: -3.6816
Max Act: 3.4625. Min Act: -0.1700
Data Index: 6293606 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19