Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4280 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.3824. Min Act: -0.1700
Data Index: 2510170 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1949. Min Act: -0.1700
Data Index: 8514027 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1044006 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1637. Min Act: -0.1700
Data Index: 7242284 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1637. Min Act: -0.1700
Data Index: 5936018 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1637. Min Act: -0.1700
Data Index: 3283838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1324. Min Act: -0.1700
Data Index: 7321685 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1324. Min Act: -0.1700
Data Index: 2647810 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 2569523 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1324. Min Act: -0.1700
Data Index: 1321002 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1324. Min Act: -0.1700
Data Index: 3279296 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 8114414 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 1441008 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 8153695 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 501236 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1324. Min Act: -0.1700
Data Index: 7685616 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 412288 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.1012. Min Act: -0.1700
Data Index: 7537047 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.0699. Min Act: -0.1700
Data Index: 3804079 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3824. Min Range: -5.3824
Max Act: 5.0699. Min Act: -0.1700
Data Index: 8332903 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19