Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.5056. Min Act: -0.1700
Data Index: 468685 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.4118. Min Act: -0.1700
Data Index: 4811852 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8134599 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3493. Min Act: -0.1700
Data Index: 2822587 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3493. Min Act: -0.1699
Data Index: 5527550 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3181. Min Act: -0.1699
Data Index: 2565681 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3181. Min Act: -0.1700
Data Index: 667855 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3181. Min Act: -0.1700
Data Index: 1865027 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.3181. Min Act: -0.1700
Data Index: 6432676 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2868. Min Act: -0.1700
Data Index: 577829 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2868. Min Act: -0.1700
Data Index: 705879 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2868. Min Act: -0.1700
Data Index: 926943 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2556. Min Act: -0.1700
Data Index: 3218042 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2556. Min Act: -0.1700
Data Index: 6867276 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2243. Min Act: -0.1700
Data Index: 2822585 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.2243. Min Act: -0.1700
Data Index: 2852647 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.1931. Min Act: -0.1700
Data Index: 1652113 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.1931. Min Act: -0.1700
Data Index: 5445097 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.1931. Min Act: -0.1700
Data Index: 726526 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5056. Min Range: -5.5056
Max Act: 5.1931. Min Act: -0.1700
Data Index: 5017944 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19