Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0509. Min Range: -6.0509
Max Act: 6.0509. Min Act: -0.1700
Data Index: 6251120 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.9259. Min Act: -0.1700
Data Index: 6905299 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8947. Min Act: -0.1700
Data Index: 6909398 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.9259. Min Act: -0.1700
Data Index: 2585174 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5286817 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8322. Min Act: -0.1700
Data Index: 1154271 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8009. Min Act: -0.1700
Data Index: 324656 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8009. Min Act: -0.1700
Data Index: 1457497 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8009. Min Act: -0.1700
Data Index: 5598512 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.8009. Min Act: -0.1700
Data Index: 7473113 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 6665003 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7697. Min Act: -0.1700
Data Index: 3262536 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7697. Min Act: -0.1700
Data Index: 13997 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7697. Min Act: -0.1700
Data Index: 140120 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2021300 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7072. Min Act: -0.1700
Data Index: 1902168 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3989078 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 2155518 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2116203 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0509. Min Range: -6.0509
Max Act: 5.7384. Min Act: -0.1700
Data Index: 5933692 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19