Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6073 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.7590. Min Act: -0.1700
Data Index: 3410304 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.7746. Min Act: -0.1700
Data Index: 8357054 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.7433. Min Act: -0.1700
Data Index: 7541371 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.6964. Min Act: -0.1700
Data Index: 157583 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.6808. Min Act: -0.1700
Data Index: 1330103 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.6338. Min Act: -0.1700
Data Index: 7054558 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5556. Min Act: -0.1700
Data Index: 7684857 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5869. Min Act: -0.1700
Data Index: 420162 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5243. Min Act: -0.1700
Data Index: 8163514 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5399. Min Act: -0.1700
Data Index: 3674151 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5556. Min Act: -0.1700
Data Index: 2870775 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5556. Min Act: -0.1700
Data Index: 8471729 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5243. Min Act: -0.1700
Data Index: 1196143 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4929. Min Act: -0.1700
Data Index: 1377163 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.5086. Min Act: -0.1700
Data Index: 8523633 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4773. Min Act: -0.1700
Data Index: 2963346 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4929. Min Act: -0.1700
Data Index: 157582 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2052050 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4616. Min Act: -0.1700
Data Index: 5129243 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7746. Min Range: -3.7746
Max Act: 3.4773. Min Act: -0.1700
Data Index: 8196369 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19