Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5830 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.9575. Min Act: -0.1700
Data Index: 684970 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.9575. Min Act: -0.1700
Data Index: 187503 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.9575. Min Act: -0.1700
Data Index: 4917583 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6766875 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.8637. Min Act: -0.1700
Data Index: 5532947 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.8325. Min Act: -0.1700
Data Index: 4968214 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.8012. Min Act: -0.1700
Data Index: 2278662 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.8012. Min Act: -0.1700
Data Index: 8519131 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7387. Min Act: -0.1700
Data Index: 2233696 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7699. Min Act: -0.1700
Data Index: 4490891 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7387. Min Act: -0.1700
Data Index: 6014828 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7387. Min Act: -0.1700
Data Index: 2457748 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7074. Min Act: -0.1700
Data Index: 7932063 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7387. Min Act: -0.1700
Data Index: 527390 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7074. Min Act: -0.1700
Data Index: 4860797 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.6762. Min Act: -0.1700
Data Index: 4490890 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7074. Min Act: -0.1700
Data Index: 5444939 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7074. Min Act: -0.1700
Data Index: 2728679 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.7074. Min Act: -0.1700
Data Index: 4582169 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9575. Min Range: -4.9575
Max Act: 4.6762. Min Act: -0.1700
Data Index: 3566790 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19