Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5742. Min Range: -12.5742
Max Act: 12.5742. Min Act: -0.1700
Data Index: 504440 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5742. Min Range: -12.5742
Max Act: 12.5117. Min Act: -0.1700
Data Index: 5924877 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5742. Min Range: -12.5742
Max Act: 12.1367. Min Act: -0.1700
Data Index: 837770 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.9492. Min Act: -0.1700
Data Index: 3779942 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.8867. Min Act: -0.1700
Data Index: 6431041 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.7617. Min Act: -0.1700
Data Index: 3348641 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.6992. Min Act: -0.1700
Data Index: 4775301 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.6367. Min Act: -0.1700
Data Index: 5631450 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.6367. Min Act: -0.1700
Data Index: 6245191 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.5742. Min Act: -0.1700
Data Index: 3170073 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.5117. Min Act: -0.1700
Data Index: 1650602 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.4492. Min Act: -0.1700
Data Index: 4479908 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.3242. Min Act: -0.1700
Data Index: 7883092 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.3242. Min Act: -0.1700
Data Index: 6003133 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.3242. Min Act: -0.1700
Data Index: 6917461 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.1992. Min Act: -0.1700
Data Index: 5549370 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.2617. Min Act: -0.1700
Data Index: 304190 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.2617. Min Act: -0.1700
Data Index: 2579077 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.2617. Min Act: -0.1700
Data Index: 2006416 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5742. Min Range: -12.5742
Max Act: 11.2617. Min Act: -0.1700
Data Index: 7179996 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19