Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6302 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.7245. Min Act: -0.1700
Data Index: 1149709 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.5995. Min Act: -0.1700
Data Index: 5914863 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.4745. Min Act: -0.1700
Data Index: 2436196 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.4120. Min Act: -0.1700
Data Index: 1061305 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2870. Min Act: -0.1700
Data Index: 5771168 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2870. Min Act: -0.1700
Data Index: 3886547 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2870. Min Act: -0.1700
Data Index: 7361676 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2870. Min Act: -0.1700
Data Index: 2178339 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2870. Min Act: -0.1700
Data Index: 8234266 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2245. Min Act: -0.1700
Data Index: 1407441 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2245. Min Act: -0.1700
Data Index: 8699069 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.2245. Min Act: -0.1700
Data Index: 3403494 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 2105348 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 1580737 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 7474070 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 146386 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 2537299 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.1620. Min Act: -0.1700
Data Index: 8822889 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.0995. Min Act: -0.1700
Data Index: 371427 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7245. Min Range: -8.7245
Max Act: 8.0995. Min Act: -0.1700
Data Index: 6893293 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19