Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0027. Min Range: -8.0027
Max Act: 8.0027. Min Act: -0.1700
Data Index: 1010953 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.8777. Min Act: -0.1700
Data Index: 2139045 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.9402. Min Act: -0.1700
Data Index: 8181552 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0027. Min Range: -8.0027
Max Act: 8.0027. Min Act: -0.1700
Data Index: 2346232 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.8777. Min Act: -0.1700
Data Index: 7952471 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.7527. Min Act: -0.1700
Data Index: 6060813 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.7527. Min Act: -0.1700
Data Index: 8050815 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6902. Min Act: -0.1700
Data Index: 7042641 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6902. Min Act: -0.1700
Data Index: 6109013 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6902. Min Act: -0.1700
Data Index: 1481526 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6902. Min Act: -0.1700
Data Index: 2290944 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6902. Min Act: -0.1700
Data Index: 7031758 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6277. Min Act: -0.1700
Data Index: 4465517 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6277. Min Act: -0.1700
Data Index: 5185944 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6277. Min Act: -0.1700
Data Index: 1376072 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6277. Min Act: -0.1700
Data Index: 7721590 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.5652. Min Act: -0.1700
Data Index: 3378423 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.5652. Min Act: -0.1700
Data Index: 8088608 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.6277. Min Act: -0.1700
Data Index: 7565046 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0027. Min Range: -8.0027
Max Act: 7.5652. Min Act: -0.1700
Data Index: 5694546 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19