Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.9821. Min Act: -0.1700
Data Index: 3230068 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 6216358 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8570. Min Act: -0.1700
Data Index: 1101261 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8570. Min Act: -0.1700
Data Index: 6878510 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8257. Min Act: -0.1700
Data Index: 8700029 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 5911569 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7945. Min Act: -0.1700
Data Index: 1653156 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6632658 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.6693. Min Act: -0.1700
Data Index: 5600391 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.6693. Min Act: -0.1700
Data Index: 5660458 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.6067. Min Act: -0.1700
Data Index: 7763997 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.6067. Min Act: -0.1700
Data Index: 6570868 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.6067. Min Act: -0.1700
Data Index: 2727419 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5441. Min Act: -0.1700
Data Index: 6966283 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5754. Min Act: -0.1700
Data Index: 4609970 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5754. Min Act: -0.1700
Data Index: 8780056 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5754. Min Act: -0.1700
Data Index: 6272746 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5441. Min Act: -0.1700
Data Index: 3053819 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5441. Min Act: -0.1700
Data Index: 1615424 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.5754. Min Act: -0.1700
Data Index: 5792031 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19