Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.3590. Min Act: -0.1700
Data Index: 1920625 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.3590. Min Act: -0.1700
Data Index: 760923 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.3590. Min Act: -0.1700
Data Index: 5335001 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.3277. Min Act: -0.1700
Data Index: 6979515 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2652. Min Act: -0.1700
Data Index: 5221739 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2965. Min Act: -0.1700
Data Index: 5345567 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2652. Min Act: -0.1700
Data Index: 7122128 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2652. Min Act: -0.1700
Data Index: 1562471 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2340. Min Act: -0.1700
Data Index: 1895228 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2340. Min Act: -0.1700
Data Index: 4306557 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2340. Min Act: -0.1700
Data Index: 8273543 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2027. Min Act: -0.1700
Data Index: 3753199 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2027. Min Act: -0.1700
Data Index: 5005645 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.1715. Min Act: -0.1700
Data Index: 2005245 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2027. Min Act: -0.1700
Data Index: 5582120 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.1715. Min Act: -0.1700
Data Index: 1025759 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.1715. Min Act: -0.1700
Data Index: 1172398 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.1715. Min Act: -0.1700
Data Index: 1168448 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.1715. Min Act: -0.1700
Data Index: 946622 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3590. Min Range: -4.3590
Max Act: 4.2027. Min Act: -0.1700
Data Index: 945462 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19