Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.7798. Min Act: -0.1700
Data Index: 2971984 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.7016. Min Act: -0.1700
Data Index: 6755629 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6860. Min Act: -0.1700
Data Index: 1937488 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6860. Min Act: -0.1700
Data Index: 3716852 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6703. Min Act: -0.1700
Data Index: 7700686 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6390. Min Act: -0.1700
Data Index: 7988798 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6703. Min Act: -0.1700
Data Index: 6482363 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6390. Min Act: -0.1700
Data Index: 6157171 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6077. Min Act: -0.1700
Data Index: 1386094 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6077. Min Act: -0.1700
Data Index: 8738143 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6077. Min Act: -0.1700
Data Index: 4414604 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5921. Min Act: -0.1700
Data Index: 1114272 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5921. Min Act: -0.1700
Data Index: 8800281 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.6077. Min Act: -0.1700
Data Index: 1466516 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5608. Min Act: -0.1700
Data Index: 5883293 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5608. Min Act: -0.1700
Data Index: 3692034 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5138. Min Act: -0.1700
Data Index: 4846369 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.5294. Min Act: -0.1700
Data Index: 3911703 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.4981. Min Act: -0.1700
Data Index: 394915 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7798. Min Range: -3.7798
Max Act: 3.4981. Min Act: -0.1700
Data Index: 3329884 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19