Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.8194. Min Act: -0.1700
Data Index: 7259170 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.7238. Min Act: -0.1700
Data Index: 7646823 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.7238. Min Act: -0.1700
Data Index: 6150719 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6918. Min Act: -0.1700
Data Index: 8253911 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6597. Min Act: -0.1700
Data Index: 4048775 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6758. Min Act: -0.1700
Data Index: 3562444 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6758. Min Act: -0.1700
Data Index: 8214447 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6597. Min Act: -0.1700
Data Index: 1973731 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6276. Min Act: -0.1700
Data Index: 3981424 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6276. Min Act: -0.1700
Data Index: 6952115 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6597. Min Act: -0.1700
Data Index: 5061590 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6115. Min Act: -0.1700
Data Index: 4412068 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6276. Min Act: -0.1700
Data Index: 2040669 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6276. Min Act: -0.1700
Data Index: 1223780 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6276. Min Act: -0.1700
Data Index: 7989882 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6115. Min Act: -0.1700
Data Index: 2087410 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.5955. Min Act: -0.1700
Data Index: 7746346 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6115. Min Act: -0.1700
Data Index: 6911856 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.6115. Min Act: -0.1700
Data Index: 6668027 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8194. Min Range: -2.8194
Max Act: 2.5955. Min Act: -0.1700
Data Index: 3660004 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19