Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6025. Min Range: -9.6025
Max Act: 9.6025. Min Act: -0.1700
Data Index: 4443708 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6025. Min Range: -9.6025
Max Act: 9.6025. Min Act: -0.1700
Data Index: 3915437 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6025. Min Range: -9.6025
Max Act: 9.2275. Min Act: -0.1700
Data Index: 2467980 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6025. Min Range: -9.6025
Max Act: 9.1650. Min Act: -0.1700
Data Index: 8830515 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.9150. Min Act: -0.1700
Data Index: 8640554 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.9150. Min Act: -0.1700
Data Index: 8460847 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.7275. Min Act: -0.1700
Data Index: 2287087 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.7275. Min Act: -0.1700
Data Index: 7337523 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.6025. Min Act: -0.1700
Data Index: 2378211 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.5400. Min Act: -0.1700
Data Index: 149210 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.4775. Min Act: -0.1700
Data Index: 6750878 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.4775. Min Act: -0.1700
Data Index: 5141111 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.4150. Min Act: -0.1700
Data Index: 315747 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.4775. Min Act: -0.1700
Data Index: 1480567 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.3525. Min Act: -0.1700
Data Index: 1688771 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.2275. Min Act: -0.1700
Data Index: 2159785 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.1650. Min Act: -0.1700
Data Index: 4872699 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.1963. Min Act: -0.1700
Data Index: 6146681 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.1025. Min Act: -0.1700
Data Index: 8538555 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6025. Min Range: -9.6025
Max Act: 8.1338. Min Act: -0.1700
Data Index: 1502942 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19