Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.5400. Min Act: -0.1700
Data Index: 2575662 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.4775. Min Act: -0.1700
Data Index: 7117107 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.3525. Min Act: -0.1700
Data Index: 7404350 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.3525. Min Act: -0.1700
Data Index: 5437281 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.2275. Min Act: -0.1700
Data Index: 5698194 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1650. Min Act: -0.1700
Data Index: 8292549 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1650. Min Act: -0.1700
Data Index: 5952511 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1650. Min Act: -0.1700
Data Index: 5279247 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1650. Min Act: -0.1700
Data Index: 2803395 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1338. Min Act: -0.1700
Data Index: 5554851 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1025. Min Act: -0.1700
Data Index: 3811926 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1025. Min Act: -0.1700
Data Index: 7995241 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1025. Min Act: -0.1700
Data Index: 571295 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.1338. Min Act: -0.1700
Data Index: 6550558 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.0400. Min Act: -0.1700
Data Index: 4019874 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.0400. Min Act: -0.1700
Data Index: 4529281 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5400. Min Range: -7.5400
Max Act: 7.0088. Min Act: -0.1700
Data Index: 8401010 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5400. Min Range: -7.5400
Max Act: 6.9775. Min Act: -0.1700
Data Index: 7870516 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5400. Min Range: -7.5400
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4239981 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5400. Min Range: -7.5400
Max Act: 6.9775. Min Act: -0.1700
Data Index: 5599674 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19