Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4402 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1984930 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.5684. Min Act: -0.1700
Data Index: 7728306 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.5372. Min Act: -0.1700
Data Index: 3792123 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.4746. Min Act: -0.1700
Data Index: 1365107 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.3809. Min Act: -0.1700
Data Index: 3930107 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.4121. Min Act: -0.1700
Data Index: 7087780 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.3809. Min Act: -0.1700
Data Index: 7844397 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.3809. Min Act: -0.1700
Data Index: 8435695 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2871. Min Act: -0.1700
Data Index: 4679952 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.3184. Min Act: -0.1700
Data Index: 6422973 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2871. Min Act: -0.1700
Data Index: 308783 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2871. Min Act: -0.1700
Data Index: 750494 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2871. Min Act: -0.1700
Data Index: 7342465 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2246. Min Act: -0.1700
Data Index: 2304446 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2246. Min Act: -0.1700
Data Index: 2872800 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2246. Min Act: -0.1700
Data Index: 1029065 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.2246. Min Act: -0.1700
Data Index: 3063915 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.1934. Min Act: -0.1700
Data Index: 7317197 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.1934. Min Act: -0.1700
Data Index: 6126787 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6934. Min Range: -4.6934
Max Act: 4.1934. Min Act: -0.1700
Data Index: 739139 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19