Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.1401. Min Act: -0.1700
Data Index: 1707367 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.1401. Min Act: -0.1700
Data Index: 4031722 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.1401. Min Act: -0.1700
Data Index: 4988969 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.1086. Min Act: -0.1700
Data Index: 3671689 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.1086. Min Act: -0.1700
Data Index: 2249545 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0928. Min Act: -0.1700
Data Index: 240620 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0613. Min Act: -0.1700
Data Index: 4394757 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0297. Min Act: -0.1700
Data Index: 6646242 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0297. Min Act: -0.1700
Data Index: 2201995 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0455. Min Act: -0.1700
Data Index: 2813843 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0297. Min Act: -0.1700
Data Index: 7624412 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0297. Min Act: -0.1700
Data Index: 6418443 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0139. Min Act: -0.1700
Data Index: 4116593 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1401. Min Range: -3.1401
Max Act: 2.9981. Min Act: -0.1700
Data Index: 2122582 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0139. Min Act: -0.1700
Data Index: 4031727 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1401. Min Range: -3.1401
Max Act: 3.0139. Min Act: -0.1700
Data Index: 8036683 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1401. Min Range: -3.1401
Max Act: 2.9981. Min Act: -0.1700
Data Index: 2813848 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1401. Min Range: -3.1401
Max Act: 2.9823. Min Act: -0.1700
Data Index: 6468700 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1401. Min Range: -3.1401
Max Act: 2.9823. Min Act: -0.1700
Data Index: 6432930 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1401. Min Range: -3.1401
Max Act: 2.9823. Min Act: -0.1700
Data Index: 2783101 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19