Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.3198. Min Act: -0.1700
Data Index: 4914828 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.1948. Min Act: -0.1700
Data Index: 2165966 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7750712 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.8823. Min Act: -0.1700
Data Index: 733680 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.8198. Min Act: -0.1700
Data Index: 5957096 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.7886. Min Act: -0.1700
Data Index: 139241 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.7573. Min Act: -0.1700
Data Index: 7411728 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6323. Min Act: -0.1700
Data Index: 3185766 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6948. Min Act: -0.1700
Data Index: 1237995 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6636. Min Act: -0.1700
Data Index: 6525589 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6011. Min Act: -0.1700
Data Index: 1886060 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6011. Min Act: -0.1700
Data Index: 3666767 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5698. Min Act: -0.1700
Data Index: 805648 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5698. Min Act: -0.1700
Data Index: 1121566 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5698. Min Act: -0.1700
Data Index: 2461805 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5386. Min Act: -0.1700
Data Index: 589579 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5386. Min Act: -0.1700
Data Index: 6086590 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5386. Min Act: -0.1700
Data Index: 5979494 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5386. Min Act: -0.1700
Data Index: 4739583 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5386. Min Act: -0.1700
Data Index: 3814684 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19