Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.9433. Min Act: -0.1700
Data Index: 5743971 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.7245. Min Act: -0.1700
Data Index: 4800417 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6620. Min Act: -0.1700
Data Index: 6277977 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6620. Min Act: -0.1700
Data Index: 7656310 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6620. Min Act: -0.1700
Data Index: 42694 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6620. Min Act: -0.1700
Data Index: 1317074 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6620. Min Act: -0.1700
Data Index: 7214384 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6308. Min Act: -0.1700
Data Index: 8810357 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.5995. Min Act: -0.1700
Data Index: 2671676 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.6308. Min Act: -0.1700
Data Index: 4497029 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.5683. Min Act: -0.1700
Data Index: 317271 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.5370. Min Act: -0.1700
Data Index: 816095 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.5058. Min Act: -0.1700
Data Index: 1653545 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4433. Min Act: -0.1700
Data Index: 7607879 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4433. Min Act: -0.1700
Data Index: 1808186 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4120. Min Act: -0.1700
Data Index: 7726144 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4120. Min Act: -0.1700
Data Index: 119951 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4120. Min Act: -0.1700
Data Index: 2819789 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.4120. Min Act: -0.1700
Data Index: 844827 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9433. Min Range: -6.9433
Max Act: 6.3808. Min Act: -0.1700
Data Index: 6800201 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19