Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5579. Min Range: -7.5579
Max Act: 7.5579. Min Act: -0.1700
Data Index: 6971782 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5579. Min Range: -7.5579
Max Act: 7.3704. Min Act: -0.1700
Data Index: 6841362 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5579. Min Range: -7.5579
Max Act: 7.1517. Min Act: -0.1700
Data Index: 4327194 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5579. Min Range: -7.5579
Max Act: 7.0267. Min Act: -0.1700
Data Index: 2701051 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9954. Min Act: -0.1700
Data Index: 1512681 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5579. Min Range: -7.5579
Max Act: 7.0267. Min Act: -0.1700
Data Index: 3784605 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9954. Min Act: -0.1700
Data Index: 1205118 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9329. Min Act: -0.1700
Data Index: 8017762 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9954. Min Act: -0.1700
Data Index: 8133413 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9954. Min Act: -0.1700
Data Index: 6454414 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9329. Min Act: -0.1700
Data Index: 5529335 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9329. Min Act: -0.1700
Data Index: 3029673 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9329. Min Act: -0.1700
Data Index: 5594837 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9017. Min Act: -0.1700
Data Index: 4415981 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.9017. Min Act: -0.1700
Data Index: 7397690 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.8704. Min Act: -0.1700
Data Index: 1473307 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.8392. Min Act: -0.1700
Data Index: 384949 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.8392. Min Act: -0.1700
Data Index: 7114943 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.8079. Min Act: -0.1700
Data Index: 6581805 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5579. Min Range: -7.5579
Max Act: 6.7767. Min Act: -0.1700
Data Index: 4676750 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19