Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2439 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0895. Min Range: -6.0895
Max Act: 6.0895. Min Act: -0.1700
Data Index: 6439978 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0895. Min Range: -6.0895
Max Act: 6.0583. Min Act: -0.1700
Data Index: 2778956 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.9020. Min Act: -0.1700
Data Index: 5940023 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.8708. Min Act: -0.1700
Data Index: 7253117 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.8395. Min Act: -0.1700
Data Index: 1973464 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.8395. Min Act: -0.1700
Data Index: 3456416 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7613579 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7458. Min Act: -0.1700
Data Index: 1009093 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7458. Min Act: -0.1700
Data Index: 7281313 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5027567 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5807298 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7145. Min Act: -0.1700
Data Index: 2438974 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.7145. Min Act: -0.1700
Data Index: 2310289 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6520. Min Act: -0.1700
Data Index: 4098298 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6833. Min Act: -0.1700
Data Index: 2216678 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7907978 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6208. Min Act: -0.1700
Data Index: 1187066 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6208. Min Act: -0.1700
Data Index: 7629441 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6833. Min Act: -0.1700
Data Index: 8427302 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0895. Min Range: -6.0895
Max Act: 5.6208. Min Act: -0.1700
Data Index: 2831353 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19