Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0721. Min Range: -5.0721
Max Act: 5.0721. Min Act: -0.1700
Data Index: 6925197 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8533. Min Act: -0.1700
Data Index: 2603946 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8533. Min Act: -0.1700
Data Index: 3851446 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8533. Min Act: -0.1700
Data Index: 2713834 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8221. Min Act: -0.1700
Data Index: 6634416 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8221. Min Act: -0.1700
Data Index: 3119441 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 5372081 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.8221. Min Act: -0.1700
Data Index: 1313132 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 8506661 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 2239433 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 5472082 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 906169 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 539180 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7596. Min Act: -0.1700
Data Index: 4675663 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 4220476 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7908. Min Act: -0.1700
Data Index: 8279132 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7596. Min Act: -0.1700
Data Index: 579517 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7596. Min Act: -0.1700
Data Index: 2978747 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7596. Min Act: -0.1700
Data Index: 588915 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0721. Min Range: -5.0721
Max Act: 4.7596. Min Act: -0.1700
Data Index: 6669619 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19