Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 2256945 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 1727671 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 8776422 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 7715343 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 6852030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 7476433 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 8617736 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 5721993 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 7183478 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 8526565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 4684966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 4330555 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9477. Min Act: -0.1700
Data Index: 2360059 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 653107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 1684313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 6940207 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 7099326 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 8032726 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.9164. Min Act: -0.1700
Data Index: 8356877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9477. Min Range: -3.9477
Max Act: 3.8852. Min Act: -0.1700
Data Index: 6551143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19