Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.7185. Min Act: -0.1700
Data Index: 5320739 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.7185. Min Act: -0.1700
Data Index: 2444601 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3075894 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.6560. Min Act: -0.1696
Data Index: 1036554 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 1497779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.6560. Min Act: -0.1700
Data Index: 7021725 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.6560. Min Act: -0.1700
Data Index: 5649626 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8310099 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.6560. Min Act: -0.1700
Data Index: 4428533 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 6949720 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 5769544 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 484456 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1699
Data Index: 52206 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 4599052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 979770 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 4502741 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3516030 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5310. Min Act: -0.1700
Data Index: 707259 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5310. Min Act: -0.1700
Data Index: 2495020 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7185. Min Range: -6.7185
Max Act: 6.5310. Min Act: -0.1700
Data Index: 117167 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19