Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3275. Min Range: -9.3275
Max Act: 9.3275. Min Act: -0.1700
Data Index: 8015940 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.7650. Min Act: -0.1700
Data Index: 7412467 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.7025. Min Act: -0.1700
Data Index: 984906 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.6400. Min Act: -0.1700
Data Index: 2846229 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.4525. Min Act: -0.1700
Data Index: 5946728 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.4525. Min Act: -0.1700
Data Index: 263856 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 7404684 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 1601815 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.3275. Min Act: -0.1700
Data Index: 7157585 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.3275. Min Act: -0.1700
Data Index: 6785929 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.2650. Min Act: -0.1700
Data Index: 3237151 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.2650. Min Act: -0.1700
Data Index: 3465055 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 3522862 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.1088. Min Act: -0.1700
Data Index: 7228185 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3275. Min Range: -9.3275
Max Act: 8.0775. Min Act: -0.1700
Data Index: 3091889 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3275. Min Range: -9.3275
Max Act: 7.9838. Min Act: -0.1700
Data Index: 4534968 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3275. Min Range: -9.3275
Max Act: 7.8275. Min Act: -0.1700
Data Index: 7153401 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3275. Min Range: -9.3275
Max Act: 7.8588. Min Act: -0.1700
Data Index: 7779971 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3275. Min Range: -9.3275
Max Act: 7.7650. Min Act: -0.1700
Data Index: 120244 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3275. Min Range: -9.3275
Max Act: 7.7963. Min Act: -0.1700
Data Index: 2852963 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19