Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4738 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.3895. Min Act: -0.1700
Data Index: 5910151 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.1082. Min Act: -0.1700
Data Index: 1766441 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.1082. Min Act: -0.1700
Data Index: 211747 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.1082. Min Act: -0.1700
Data Index: 355073 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.0770. Min Act: -0.1700
Data Index: 8027953 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.0457. Min Act: -0.1700
Data Index: 4685146 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.0457. Min Act: -0.1700
Data Index: 3829550 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3895. Min Range: -5.3895
Max Act: 5.0145. Min Act: -0.1700
Data Index: 8416127 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.9832. Min Act: -0.1700
Data Index: 3413035 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.9520. Min Act: -0.1700
Data Index: 6430814 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.9520. Min Act: -0.1700
Data Index: 5616267 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3033094 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.8582. Min Act: -0.1700
Data Index: 1021098 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.8895. Min Act: -0.1700
Data Index: 7783993 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.9207. Min Act: -0.1700
Data Index: 6911784 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.7645. Min Act: -0.1700
Data Index: 3694011 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.7957. Min Act: -0.1700
Data Index: 5204189 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.7645. Min Act: -0.1700
Data Index: 6256848 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.7645. Min Act: -0.1700
Data Index: 3372969 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3895. Min Range: -5.3895
Max Act: 4.7645. Min Act: -0.1700
Data Index: 1160402 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19