Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7060453 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7403101 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.1356. Min Act: -0.1700
Data Index: 4460952 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.0731. Min Act: -0.1700
Data Index: 1869832 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2294. Min Range: -6.2294
Max Act: 6.0419. Min Act: -0.1700
Data Index: 3375139 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.8544. Min Act: -0.1700
Data Index: 1961952 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7919. Min Act: -0.1700
Data Index: 1833675 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7606. Min Act: -0.1700
Data Index: 1497011 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7919. Min Act: -0.1700
Data Index: 1897494 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.7294. Min Act: -0.1700
Data Index: 919936 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6981. Min Act: -0.1700
Data Index: 8661187 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6981. Min Act: -0.1700
Data Index: 808843 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6669. Min Act: -0.1700
Data Index: 3527742 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6669. Min Act: -0.1700
Data Index: 6161805 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 4572019 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6669. Min Act: -0.1700
Data Index: 4034719 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6356. Min Act: -0.1700
Data Index: 8526170 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6356. Min Act: -0.1700
Data Index: 1669737 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6356. Min Act: -0.1700
Data Index: 1206108 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2294. Min Range: -6.2294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 3472373 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19