Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0675. Min Range: -1.0675
Max Act: 1.0675. Min Act: -0.1700
Data Index: 1204135 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.8774. Min Act: -0.1700
Data Index: 1293005 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.8097. Min Act: -0.1700
Data Index: 4667 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.8097. Min Act: -0.1700
Data Index: 7921024 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7929. Min Act: -0.1700
Data Index: 8003800 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7595. Min Act: -0.1700
Data Index: 5075566 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7513. Min Act: -0.1700
Data Index: 2923370 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7430. Min Act: -0.1700
Data Index: 2840354 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7347. Min Act: -0.1699
Data Index: 4730666 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7430. Min Act: -0.1700
Data Index: 2059904 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.7101. Min Act: -0.1700
Data Index: 7850707 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6938. Min Act: -0.1700
Data Index: 1904313 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6938. Min Act: -0.1700
Data Index: 7854908 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6775. Min Act: -0.1700
Data Index: 4495027 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6856. Min Act: -0.1700
Data Index: 8620565 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6775. Min Act: -0.1700
Data Index: 8062846 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6694. Min Act: -0.1700
Data Index: 1904316 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6694. Min Act: -0.1696
Data Index: 3735086 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6694. Min Act: -0.1700
Data Index: 2584668 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0675. Min Range: -1.0675
Max Act: 0.6694. Min Act: -0.1700
Data Index: 2555276 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19