Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.8704. Min Act: -0.1700
Data Index: 3898117 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.8391. Min Act: -0.1700
Data Index: 578322 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.8391. Min Act: -0.1700
Data Index: 598964 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.8079. Min Act: -0.1700
Data Index: 4679504 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.8079. Min Act: -0.1700
Data Index: 7784065 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 2715796 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 6607655 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 6287678 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 5028961 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 1272953 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7766. Min Act: -0.1700
Data Index: 7681779 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7454. Min Act: -0.1700
Data Index: 4599041 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7454. Min Act: -0.1700
Data Index: 2757833 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7141. Min Act: -0.1700
Data Index: 4879549 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7141. Min Act: -0.1700
Data Index: 5243082 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7141. Min Act: -0.1700
Data Index: 4277240 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.6829. Min Act: -0.1700
Data Index: 2090983 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.7141. Min Act: -0.1700
Data Index: 3061886 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.6829. Min Act: -0.1700
Data Index: 7215651 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8704. Min Range: -4.8704
Max Act: 4.6829. Min Act: -0.1700
Data Index: 5153140 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19