Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.7679. Min Act: -0.1700
Data Index: 8128199 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.7366. Min Act: -0.1700
Data Index: 4764123 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.7054. Min Act: -0.1700
Data Index: 1887919 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.6741. Min Act: -0.1700
Data Index: 4617999 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.6741. Min Act: -0.1700
Data Index: 8295541 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.6429. Min Act: -0.1700
Data Index: 5613782 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5804. Min Act: -0.1700
Data Index: 62320 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.6116. Min Act: -0.1700
Data Index: 7681265 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5804. Min Act: -0.1700
Data Index: 7491341 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5804. Min Act: -0.1700
Data Index: 2587847 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 3002767 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5491. Min Act: -0.1700
Data Index: 3597631 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 5765207 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 6704797 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 1972629 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 8490345 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.4866. Min Act: -0.1700
Data Index: 2600041 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.4866. Min Act: -0.1700
Data Index: 2804951 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.5179. Min Act: -0.1700
Data Index: 7720707 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7679. Min Range: -4.7679
Max Act: 4.4866. Min Act: -0.1700
Data Index: 6028041 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19