Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0823. Min Range: -8.0823
Max Act: 8.0823. Min Act: -0.1700
Data Index: 8419524 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.4885. Min Act: -0.1700
Data Index: 5481970 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.2073. Min Act: -0.1700
Data Index: 3206212 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6135002 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.0198. Min Act: -0.1700
Data Index: 2915511 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.0198. Min Act: -0.1700
Data Index: 5711304 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0823. Min Range: -8.0823
Max Act: 7.0198. Min Act: -0.1700
Data Index: 7425408 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.9573. Min Act: -0.1700
Data Index: 593922 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.9573. Min Act: -0.1700
Data Index: 4876287 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.9573. Min Act: -0.1700
Data Index: 5585274 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8635. Min Act: -0.1700
Data Index: 2439237 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8635. Min Act: -0.1700
Data Index: 4786517 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8635. Min Act: -0.1700
Data Index: 7838072 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8635. Min Act: -0.1700
Data Index: 1813044 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8323. Min Act: -0.1700
Data Index: 4180981 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8010. Min Act: -0.1700
Data Index: 1835928 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.8010. Min Act: -0.1700
Data Index: 538616 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 7096246 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 504155 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0823. Min Range: -8.0823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 4901324 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19