Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.9035. Min Act: -0.1700
Data Index: 8721762 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.7160. Min Act: -0.1700
Data Index: 6040544 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.7160. Min Act: -0.1700
Data Index: 5222173 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.6535. Min Act: -0.1700
Data Index: 1544887 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5910. Min Act: -0.1700
Data Index: 2435636 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.6222. Min Act: -0.1700
Data Index: 1571300 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5910. Min Act: -0.1700
Data Index: 4366743 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5597. Min Act: -0.1700
Data Index: 4986353 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5597. Min Act: -0.1700
Data Index: 8166951 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5285. Min Act: -0.1700
Data Index: 2529423 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5285. Min Act: -0.1700
Data Index: 4986354 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.5597. Min Act: -0.1700
Data Index: 5182412 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 241418 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4437969 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 1236234 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 8682959 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 3595283 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4347. Min Act: -0.1700
Data Index: 1976035 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4660. Min Act: -0.1700
Data Index: 3564145 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9035. Min Range: -5.9035
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4553715 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19