Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.2791. Min Act: -0.1700
Data Index: 6555979 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.2166. Min Act: -0.1700
Data Index: 1066338 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.1854. Min Act: -0.1700
Data Index: 4300893 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7879455 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.0916. Min Act: -0.1700
Data Index: 3844899 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.0604. Min Act: -0.1700
Data Index: 6559565 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.0291. Min Act: -0.1700
Data Index: 5492564 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.0291. Min Act: -0.1700
Data Index: 1123335 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2791. Min Range: -6.2791
Max Act: 6.0291. Min Act: -0.1700
Data Index: 2656480 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9354. Min Act: -0.1700
Data Index: 3320080 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9354. Min Act: -0.1700
Data Index: 8446616 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9354. Min Act: -0.1700
Data Index: 8708825 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.8729. Min Act: -0.1700
Data Index: 4934522 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9041. Min Act: -0.1700
Data Index: 1001289 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9041. Min Act: -0.1700
Data Index: 6761297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5610514 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.8729. Min Act: -0.1700
Data Index: 6168782 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.9041. Min Act: -0.1700
Data Index: 6788900 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.8729. Min Act: -0.1700
Data Index: 722584 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2791. Min Range: -6.2791
Max Act: 5.8729. Min Act: -0.1700
Data Index: 5439728 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19