Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2654. Min Range: -5.2654
Max Act: 5.2654. Min Act: -0.1700
Data Index: 3963049 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2654. Min Range: -5.2654
Max Act: 5.1716. Min Act: -0.1700
Data Index: 3339717 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2654. Min Range: -5.2654
Max Act: 5.1404. Min Act: -0.1700
Data Index: 2893889 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2654. Min Range: -5.2654
Max Act: 5.0779. Min Act: -0.1700
Data Index: 3424821 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2654. Min Range: -5.2654
Max Act: 5.0466. Min Act: -0.1700
Data Index: 1206740 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9841. Min Act: -0.1700
Data Index: 3628446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9841. Min Act: -0.1700
Data Index: 8172381 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9841. Min Act: -0.1700
Data Index: 5332232 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9841. Min Act: -0.1700
Data Index: 1008406 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9529. Min Act: -0.1700
Data Index: 2453018 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9529. Min Act: -0.1700
Data Index: 1627951 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9216. Min Act: -0.1700
Data Index: 654927 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9216. Min Act: -0.1700
Data Index: 4368890 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8904. Min Act: -0.1700
Data Index: 7903974 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.9216. Min Act: -0.1700
Data Index: 8128270 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8904. Min Act: -0.1700
Data Index: 7098073 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8591. Min Act: -0.1700
Data Index: 3567348 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8904. Min Act: -0.1700
Data Index: 7203363 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8904. Min Act: -0.1700
Data Index: 2420636 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2654. Min Range: -5.2654
Max Act: 4.8591. Min Act: -0.1700
Data Index: 6199005 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19