Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 285322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 3883715 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 5150403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 415792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 3140609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 1452585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 3107735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 2761146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 642094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.9218. Min Act: -0.1700
Data Index: 1895418 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8905. Min Act: -0.1700
Data Index: 12932 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8905. Min Act: -0.1700
Data Index: 3414723 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8905. Min Act: -0.1700
Data Index: 7279993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8905. Min Act: -0.1700
Data Index: 8410815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 1844190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 7115223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 6913016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 6820019 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 7786333 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9218. Min Range: -3.9218
Max Act: 3.8593. Min Act: -0.1700
Data Index: 6718330 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19