Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.7052. Min Act: -0.1700
Data Index: 3066376 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.7052. Min Act: -0.1700
Data Index: 376831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.7052. Min Act: -0.1700
Data Index: 4468273 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6739. Min Act: -0.1700
Data Index: 7314392 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6426. Min Act: -0.1700
Data Index: 2224611 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6426. Min Act: -0.1700
Data Index: 778104 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6113. Min Act: -0.1700
Data Index: 8734508 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6113. Min Act: -0.1700
Data Index: 724529 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.6113. Min Act: -0.1700
Data Index: 4999634 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5487. Min Act: -0.1700
Data Index: 5040197 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 737000 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 1628600 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 1595801 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 5485801 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5487. Min Act: -0.1700
Data Index: 1890755 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 6394095 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5487. Min Act: -0.1700
Data Index: 6297217 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5800. Min Act: -0.1700
Data Index: 5449738 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5487. Min Act: -0.1700
Data Index: 8345858 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7052. Min Range: -3.7052
Max Act: 3.5487. Min Act: -0.1700
Data Index: 245074 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19