Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4595 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8747. Min Act: -0.1700
Data Index: 1485805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 4095043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 4109583 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 7033789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1737223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1434850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1034565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1104516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 651985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 6780681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1671870 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 6635113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 5927955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 5886628 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 5594860 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4704877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4647528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4524497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8434. Min Act: -0.1700
Data Index: 256385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8747. Min Range: -3.8747
Max Act: 3.8121. Min Act: -0.1700
Data Index: 462497 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19