Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.8365. Min Act: -0.1700
Data Index: 4667307 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 3367966 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 582848 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7740. Min Act: -0.1700
Data Index: 4862830 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7740. Min Act: -0.1700
Data Index: 602858 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7740. Min Act: -0.1700
Data Index: 8437895 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7740. Min Act: -0.1700
Data Index: 7859775 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 8812900 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 3090179 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 1566724 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 8557656 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7115. Min Act: -0.1700
Data Index: 1078127 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 2133201 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 7941638 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 6960751 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 771437 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 5370758 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 3042 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7427. Min Act: -0.1700
Data Index: 4795372 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8365. Min Range: -7.8365
Max Act: 7.7740. Min Act: -0.1700
Data Index: 3895134 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19