Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5284 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.5025. Min Act: -0.1700
Data Index: 8699011 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.2213. Min Act: -0.1700
Data Index: 6126761 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.1275. Min Act: -0.1700
Data Index: 1130934 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.1275. Min Act: -0.1700
Data Index: 6733887 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.0963. Min Act: -0.1700
Data Index: 866453 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.0963. Min Act: -0.1700
Data Index: 46853 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5025. Min Range: -7.5025
Max Act: 7.0338. Min Act: -0.1700
Data Index: 8483282 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.9713. Min Act: -0.1700
Data Index: 6703614 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.9088. Min Act: -0.1700
Data Index: 7842406 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.9400. Min Act: -0.1700
Data Index: 5144299 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.9088. Min Act: -0.1700
Data Index: 7672681 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 8381815 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 2676462 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 2781083 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 3608527 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8463. Min Act: -0.1700
Data Index: 8080817 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8463. Min Act: -0.1700
Data Index: 3129746 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.7838. Min Act: -0.1700
Data Index: 5408167 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8150. Min Act: -0.1700
Data Index: 5064520 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5025. Min Range: -7.5025
Max Act: 6.8150. Min Act: -0.1700
Data Index: 3754781 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19