Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5477 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.5963. Min Act: -0.1700
Data Index: 1084608 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.5025. Min Act: -0.1700
Data Index: 4117230 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.4400. Min Act: -0.1700
Data Index: 6588248 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.3150. Min Act: -0.1700
Data Index: 7739692 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.2525. Min Act: -0.1700
Data Index: 4916932 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1900. Min Act: -0.1700
Data Index: 1895034 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1900. Min Act: -0.1700
Data Index: 4861170 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1588. Min Act: -0.1700
Data Index: 6235628 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1588. Min Act: -0.1700
Data Index: 4936847 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1275. Min Act: -0.1700
Data Index: 4740228 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5936822 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0963. Min Act: -0.1700
Data Index: 3221896 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0963. Min Act: -0.1700
Data Index: 6288894 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0963. Min Act: -0.1700
Data Index: 2540648 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0963. Min Act: -0.1700
Data Index: 796159 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0650. Min Act: -0.1700
Data Index: 5865226 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6513038 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6587908 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0650. Min Act: -0.1700
Data Index: 4209619 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5963. Min Range: -5.5963
Max Act: 5.0650. Min Act: -0.1700
Data Index: 3966336 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19