Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2045. Min Range: -7.2045
Max Act: 7.2045. Min Act: -0.1700
Data Index: 1965145 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.9545. Min Act: -0.1700
Data Index: 7439392 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.9233. Min Act: -0.1700
Data Index: 1037027 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7983. Min Act: -0.1700
Data Index: 3603975 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7983. Min Act: -0.1700
Data Index: 4726679 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7670. Min Act: -0.1700
Data Index: 4991494 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7358. Min Act: -0.1700
Data Index: 5821217 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7670. Min Act: -0.1700
Data Index: 6867111 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7358. Min Act: -0.1700
Data Index: 8634652 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7045. Min Act: -0.1700
Data Index: 8519867 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.7358. Min Act: -0.1700
Data Index: 3052138 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6733. Min Act: -0.1700
Data Index: 7755783 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6420. Min Act: -0.1700
Data Index: 3701580 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6733. Min Act: -0.1700
Data Index: 1329024 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6420. Min Act: -0.1700
Data Index: 5910453 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6420. Min Act: -0.1700
Data Index: 5512441 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6733. Min Act: -0.1700
Data Index: 1706421 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3488070 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6108. Min Act: -0.1700
Data Index: 5544071 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2045. Min Range: -7.2045
Max Act: 6.6108. Min Act: -0.1700
Data Index: 2958204 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19