Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.6056. Min Act: -0.1700
Data Index: 2863215 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.2931. Min Act: -0.1700
Data Index: 4563490 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.1681. Min Act: -0.1700
Data Index: 433993 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.0743. Min Act: -0.1700
Data Index: 2631881 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4149691 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.0431. Min Act: -0.1700
Data Index: 5232921 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1127268 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6056. Min Range: -5.6056
Max Act: 5.0118. Min Act: -0.1700
Data Index: 713307 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 3971855 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9806. Min Act: -0.1700
Data Index: 1179577 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9493. Min Act: -0.1700
Data Index: 934544 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9493. Min Act: -0.1700
Data Index: 471260 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9181. Min Act: -0.1700
Data Index: 4051140 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.8868. Min Act: -0.1700
Data Index: 5208133 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9181. Min Act: -0.1700
Data Index: 1903239 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9493. Min Act: -0.1700
Data Index: 1582136 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9181. Min Act: -0.1700
Data Index: 7799017 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.9181. Min Act: -0.1700
Data Index: 6917344 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.8868. Min Act: -0.1700
Data Index: 4425556 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6056. Min Range: -5.6056
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2806385 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19