Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6339 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.9120. Min Act: -0.1699
Data Index: 8586025 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.9292. Min Act: -0.1678
Data Index: 4478941 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8778. Min Act: -0.1700
Data Index: 6957801 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8778. Min Act: -0.1700
Data Index: 1394711 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8864. Min Act: -0.1700
Data Index: 5891305 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8778. Min Act: -0.1700
Data Index: 5009939 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8864. Min Act: -0.1700
Data Index: 8012082 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8693. Min Act: -0.1700
Data Index: 2047021 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8608. Min Act: -0.1696
Data Index: 3793753 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8523. Min Act: -0.1694
Data Index: 6485784 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8439. Min Act: -0.1680
Data Index: 4934760 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8523. Min Act: -0.1700
Data Index: 4585563 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8439. Min Act: -0.1700
Data Index: 413341 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8354. Min Act: -0.1700
Data Index: 8718285 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8354. Min Act: -0.1700
Data Index: 2729771 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8185. Min Act: -0.1700
Data Index: 2487842 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8270. Min Act: -0.1681
Data Index: 2149431 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8185. Min Act: -0.1695
Data Index: 4442764 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8101. Min Act: -0.1700
Data Index: 1758451 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9292. Min Range: -0.9292
Max Act: 0.8185. Min Act: -0.1700
Data Index: 6068070 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19