Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.5558. Min Act: -0.1700
Data Index: 644398 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.4933. Min Act: -0.1700
Data Index: 8712399 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.3683. Min Act: -0.1700
Data Index: 1437137 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.3683. Min Act: -0.1700
Data Index: 8771039 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.4308. Min Act: -0.1700
Data Index: 1829412 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.2433. Min Act: -0.1700
Data Index: 1801874 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.2433. Min Act: -0.1700
Data Index: 3586609 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.1808. Min Act: -0.1700
Data Index: 7209766 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.1183. Min Act: -0.1700
Data Index: 5532827 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5558. Min Range: -10.5558
Max Act: 10.0558. Min Act: -0.1700
Data Index: 4207237 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9933. Min Act: -0.1700
Data Index: 993959 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9933. Min Act: -0.1700
Data Index: 6432612 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9308. Min Act: -0.1700
Data Index: 7380380 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9308. Min Act: -0.1700
Data Index: 4837005 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9308. Min Act: -0.1700
Data Index: 8501696 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9308. Min Act: -0.1700
Data Index: 1146328 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.9308. Min Act: -0.1700
Data Index: 4556841 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.8683. Min Act: -0.1700
Data Index: 3020078 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.8058. Min Act: -0.1700
Data Index: 4202146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5558. Min Range: -10.5558
Max Act: 9.8058. Min Act: -0.1700
Data Index: 2159135 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19