Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1775. Min Act: -0.1700
Data Index: 7351505 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1463. Min Act: -0.1700
Data Index: 2008773 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3921920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1463. Min Act: -0.1700
Data Index: 4448207 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1463. Min Act: -0.1700
Data Index: 1542434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5397191 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2702004 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.0525. Min Act: -0.1700
Data Index: 5807449 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.0525. Min Act: -0.1700
Data Index: 1195645 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1775. Min Range: -5.1775
Max Act: 5.0213. Min Act: -0.1700
Data Index: 8370349 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9900. Min Act: -0.1700
Data Index: 2588492 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9900. Min Act: -0.1700
Data Index: 6751261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9900. Min Act: -0.1700
Data Index: 2762848 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9588. Min Act: -0.1700
Data Index: 6660200 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9588. Min Act: -0.1700
Data Index: 4448187 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9588. Min Act: -0.1700
Data Index: 6682686 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9588. Min Act: -0.1700
Data Index: 4541301 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9588. Min Act: -0.1700
Data Index: 6749858 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.8963. Min Act: -0.1700
Data Index: 1847367 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1775. Min Range: -5.1775
Max Act: 4.9275. Min Act: -0.1700
Data Index: 6595034 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19