Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.5065. Min Act: -0.1700
Data Index: 5790541 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.5065. Min Act: -0.1700
Data Index: 8302434 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4595. Min Act: -0.1700
Data Index: 5727944 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4595. Min Act: -0.1700
Data Index: 6227169 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4595. Min Act: -0.1700
Data Index: 6441318 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4438. Min Act: -0.1700
Data Index: 8136633 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4281. Min Act: -0.1700
Data Index: 7485664 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4281. Min Act: -0.1700
Data Index: 871432 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4125. Min Act: -0.1700
Data Index: 2243579 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.4125. Min Act: -0.1700
Data Index: 2843580 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3968. Min Act: -0.1700
Data Index: 1461774 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3968. Min Act: -0.1700
Data Index: 2004530 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3968. Min Act: -0.1700
Data Index: 493225 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3968. Min Act: -0.1700
Data Index: 1374222 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3654. Min Act: -0.1700
Data Index: 3421355 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3811. Min Act: -0.1700
Data Index: 8722047 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3811. Min Act: -0.1700
Data Index: 6526783 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3811. Min Act: -0.1700
Data Index: 1902258 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3654. Min Act: -0.1700
Data Index: 5134079 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5065. Min Range: -3.5065
Max Act: 3.3654. Min Act: -0.1700
Data Index: 6703625 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19