Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1614. Min Range: -8.1614
Max Act: 8.1614. Min Act: -0.1700
Data Index: 6223244 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1614. Min Range: -8.1614
Max Act: 8.0364. Min Act: -0.1700
Data Index: 4878325 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1614. Min Range: -8.1614
Max Act: 8.0364. Min Act: -0.1700
Data Index: 805395 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1614. Min Range: -8.1614
Max Act: 8.0051. Min Act: -0.1700
Data Index: 724691 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.9739. Min Act: -0.1700
Data Index: 3252322 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.7239. Min Act: -0.1700
Data Index: 6897386 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.6926. Min Act: -0.1700
Data Index: 6523250 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.6614. Min Act: -0.1700
Data Index: 7944521 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5989. Min Act: -0.1700
Data Index: 5827171 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5676. Min Act: -0.1700
Data Index: 6501750 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5989. Min Act: -0.1700
Data Index: 6617462 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5676. Min Act: -0.1700
Data Index: 1748301 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5364. Min Act: -0.1700
Data Index: 724690 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5051. Min Act: -0.1700
Data Index: 6455233 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.5051. Min Act: -0.1700
Data Index: 8564431 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.4739. Min Act: -0.1700
Data Index: 6884625 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.4739. Min Act: -0.1700
Data Index: 2336365 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.4426. Min Act: -0.1700
Data Index: 8513453 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.4426. Min Act: -0.1700
Data Index: 1785220 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1614. Min Range: -8.1614
Max Act: 7.4114. Min Act: -0.1700
Data Index: 462743 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19