Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5438 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.9976. Min Act: -0.1700
Data Index: 5377315 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.9663. Min Act: -0.1700
Data Index: 8789578 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.8100. Min Act: -0.1700
Data Index: 7427807 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7944. Min Act: -0.1700
Data Index: 5010392 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.8100. Min Act: -0.1700
Data Index: 7695345 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7944. Min Act: -0.1700
Data Index: 1666114 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7787. Min Act: -0.1700
Data Index: 3077152 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7631. Min Act: -0.1700
Data Index: 3463072 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7475. Min Act: -0.1700
Data Index: 8760942 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7162. Min Act: -0.1700
Data Index: 67041 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.7005. Min Act: -0.1700
Data Index: 757123 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6849. Min Act: -0.1700
Data Index: 1130743 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6692. Min Act: -0.1700
Data Index: 6455562 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6692. Min Act: -0.1700
Data Index: 8079793 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6536. Min Act: -0.1700
Data Index: 2260590 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6536. Min Act: -0.1700
Data Index: 5109619 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6692. Min Act: -0.1700
Data Index: 836797 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6536. Min Act: -0.1700
Data Index: 2133246 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6379. Min Act: -0.1700
Data Index: 8177461 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9976. Min Range: -3.9976
Max Act: 3.6379. Min Act: -0.1700
Data Index: 7812344 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19