Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.1824. Min Act: -0.1700
Data Index: 8083948 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0262. Min Act: -0.1700
Data Index: 8332697 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0262. Min Act: -0.1700
Data Index: 3349807 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9949. Min Act: -0.1700
Data Index: 4914976 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9637. Min Act: -0.1700
Data Index: 8043393 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9637. Min Act: -0.1700
Data Index: 6378127 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8387. Min Act: -0.1700
Data Index: 8452528 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8387. Min Act: -0.1700
Data Index: 8594313 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8074. Min Act: -0.1700
Data Index: 6469262 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.7762. Min Act: -0.1700
Data Index: 5202017 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.7449. Min Act: -0.1700
Data Index: 1309753 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6824. Min Act: -0.1700
Data Index: 3026036 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6824. Min Act: -0.1700
Data Index: 5842358 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6824. Min Act: -0.1700
Data Index: 6904129 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6512. Min Act: -0.1700
Data Index: 2611211 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6512. Min Act: -0.1700
Data Index: 6580210 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6199. Min Act: -0.1700
Data Index: 4171534 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.5887. Min Act: -0.1700
Data Index: 1621695 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6199. Min Act: -0.1700
Data Index: 4556137 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.6199. Min Act: -0.1700
Data Index: 4151397 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19