Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.3501. Min Act: -0.1700
Data Index: 3782568 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.3188. Min Act: -0.1700
Data Index: 8520583 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.2876. Min Act: -0.1700
Data Index: 4188354 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.2563. Min Act: -0.1700
Data Index: 8528950 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.2563. Min Act: -0.1700
Data Index: 5059384 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.2251. Min Act: -0.1700
Data Index: 6594194 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.2251. Min Act: -0.1700
Data Index: 1281060 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1938. Min Act: -0.1700
Data Index: 4994635 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1938. Min Act: -0.1700
Data Index: 7110480 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1626. Min Act: -0.1700
Data Index: 5075958 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1626. Min Act: -0.1700
Data Index: 2714105 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1626. Min Act: -0.1700
Data Index: 8330001 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1313. Min Act: -0.1700
Data Index: 4978993 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1313. Min Act: -0.1700
Data Index: 7787826 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1313. Min Act: -0.1700
Data Index: 5143446 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2641922 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2641918 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1001. Min Act: -0.1700
Data Index: 5319550 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.1001. Min Act: -0.1700
Data Index: 8693154 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3501. Min Range: -6.3501
Max Act: 6.0688. Min Act: -0.1700
Data Index: 1513275 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19