Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3981. Min Range: -8.3981
Max Act: 8.3981. Min Act: -0.1700
Data Index: 4852696 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3981. Min Range: -8.3981
Max Act: 8.3981. Min Act: -0.1700
Data Index: 2772866 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3981. Min Range: -8.3981
Max Act: 8.0856. Min Act: -0.1700
Data Index: 887680 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.9918. Min Act: -0.1700
Data Index: 7724459 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.9606. Min Act: -0.1700
Data Index: 1577793 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.9606. Min Act: -0.1700
Data Index: 572366 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.9293. Min Act: -0.1700
Data Index: 8318577 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8668. Min Act: -0.1700
Data Index: 3199911 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8668. Min Act: -0.1700
Data Index: 2265821 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8668. Min Act: -0.1700
Data Index: 6847075 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8356. Min Act: -0.1700
Data Index: 6595117 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8356. Min Act: -0.1700
Data Index: 3831248 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8043. Min Act: -0.1700
Data Index: 7571485 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.8043. Min Act: -0.1700
Data Index: 7164654 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.7731. Min Act: -0.1700
Data Index: 3070850 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.7731. Min Act: -0.1700
Data Index: 5020385 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2265819 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.7731. Min Act: -0.1700
Data Index: 53633 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.7418. Min Act: -0.1700
Data Index: 5910516 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3981. Min Range: -8.3981
Max Act: 7.6793. Min Act: -0.1700
Data Index: 7177057 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19