Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1937 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5103. Min Range: -6.5103
Max Act: 6.5103. Min Act: -0.1700
Data Index: 315818 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5103. Min Range: -6.5103
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4386815 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.9478. Min Act: -0.1700
Data Index: 7852704 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.9166. Min Act: -0.1700
Data Index: 302142 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.8541. Min Act: -0.1700
Data Index: 685548 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.8228. Min Act: -0.1700
Data Index: 5047998 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.8228. Min Act: -0.1700
Data Index: 1021125 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.7916. Min Act: -0.1700
Data Index: 4858605 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.8228. Min Act: -0.1700
Data Index: 6653692 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.7603. Min Act: -0.1700
Data Index: 4848135 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.7603. Min Act: -0.1700
Data Index: 2079815 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.7603. Min Act: -0.1700
Data Index: 4611465 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.7916. Min Act: -0.1700
Data Index: 5102359 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6978. Min Act: -0.1700
Data Index: 4725444 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6362439 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6978. Min Act: -0.1700
Data Index: 1473613 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6978. Min Act: -0.1700
Data Index: 3964345 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2970723 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6022150 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5103. Min Range: -6.5103
Max Act: 5.6666. Min Act: -0.1700
Data Index: 4464755 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19