Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 579 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.7529. Min Act: -0.1700
Data Index: 144366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.6591. Min Act: -0.1700
Data Index: 6869155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.6278. Min Act: -0.1700
Data Index: 7259738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5965. Min Act: -0.1700
Data Index: 5609264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5652. Min Act: -0.1700
Data Index: 3050649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5652. Min Act: -0.1700
Data Index: 3208346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 7509355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 8115736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 3653801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 4605365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 1115308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 2250903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5339. Min Act: -0.1700
Data Index: 2388400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5025. Min Act: -0.1700
Data Index: 7187200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5025. Min Act: -0.1700
Data Index: 4496115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5025. Min Act: -0.1700
Data Index: 3935592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.5025. Min Act: -0.1700
Data Index: 4494744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.4712. Min Act: -0.1700
Data Index: 8826144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.4712. Min Act: -0.1700
Data Index: 4303483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7529. Min Range: -3.7529
Max Act: 3.4712. Min Act: -0.1700
Data Index: 3308433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19