Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.8812. Min Act: -0.1700
Data Index: 4640499 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.5687. Min Act: -0.1700
Data Index: 2260835 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.5062. Min Act: -0.1700
Data Index: 758039 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.3187. Min Act: -0.1700
Data Index: 4834741 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.1937. Min Act: -0.1700
Data Index: 439300 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.0062. Min Act: -0.1700
Data Index: 8037108 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8812. Min Range: -9.8812
Max Act: 9.0062. Min Act: -0.1700
Data Index: 910356 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.9437. Min Act: -0.1700
Data Index: 8358320 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.9437. Min Act: -0.1700
Data Index: 4687237 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.8812. Min Act: -0.1700
Data Index: 7201892 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.8812. Min Act: -0.1700
Data Index: 6055441 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.8187. Min Act: -0.1700
Data Index: 5479761 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.7562. Min Act: -0.1700
Data Index: 1087597 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.7562. Min Act: -0.1700
Data Index: 7182228 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.7562. Min Act: -0.1700
Data Index: 5706303 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.6937. Min Act: -0.1700
Data Index: 962693 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.6937. Min Act: -0.1700
Data Index: 2014923 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.5687. Min Act: -0.1700
Data Index: 2073994 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.6312. Min Act: -0.1700
Data Index: 1771417 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8812. Min Range: -9.8812
Max Act: 8.5687. Min Act: -0.1700
Data Index: 232030 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19