Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6103 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.8530. Min Act: -0.1700
Data Index: 3950804 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.7575. Min Act: -0.1700
Data Index: 8497439 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.7096. Min Act: -0.1700
Data Index: 2453833 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.7096. Min Act: -0.1700
Data Index: 1097934 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6936. Min Act: -0.1700
Data Index: 5568014 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6776. Min Act: -0.1700
Data Index: 7737000 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6776. Min Act: -0.1700
Data Index: 255085 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6776. Min Act: -0.1700
Data Index: 8248547 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6615. Min Act: -0.1700
Data Index: 8180751 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6615. Min Act: -0.1700
Data Index: 5576918 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6615. Min Act: -0.1700
Data Index: 3436779 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6615. Min Act: -0.1700
Data Index: 8223405 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6615. Min Act: -0.1700
Data Index: 475477 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 4287894 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 4387881 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 1663050 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 6131239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 79593 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 3128584 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8530. Min Range: -2.8530
Max Act: 2.6455. Min Act: -0.1700
Data Index: 6350131 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19