Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2129 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4931. Min Act: -0.1700
Data Index: 6445548 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.9306. Min Act: -0.1700
Data Index: 4247933 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8681. Min Act: -0.1700
Data Index: 4470169 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8681. Min Act: -0.1700
Data Index: 4237244 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8681. Min Act: -0.1700
Data Index: 941612 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8368. Min Act: -0.1700
Data Index: 8451829 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8368. Min Act: -0.1700
Data Index: 8183663 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.8056. Min Act: -0.1700
Data Index: 2057108 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5697954 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.7743. Min Act: -0.1700
Data Index: 3389449 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.6806. Min Act: -0.1700
Data Index: 829359 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.6806. Min Act: -0.1700
Data Index: 3875163 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.6493. Min Act: -0.1700
Data Index: 5421934 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.6806. Min Act: -0.1700
Data Index: 567041 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.5868. Min Act: -0.1700
Data Index: 1377513 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.5868. Min Act: -0.1700
Data Index: 3551623 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.5868. Min Act: -0.1700
Data Index: 6668515 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.5868. Min Act: -0.1700
Data Index: 8797752 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 6395692 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4931. Min Range: -6.4931
Max Act: 5.5556. Min Act: -0.1700
Data Index: 693356 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19