Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2414 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2494. Min Range: -8.2494
Max Act: 8.2494. Min Act: -0.1700
Data Index: 2590907 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2494. Min Range: -8.2494
Max Act: 8.1869. Min Act: -0.1700
Data Index: 4110161 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2494. Min Range: -8.2494
Max Act: 8.1869. Min Act: -0.1700
Data Index: 1933840 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.9994. Min Act: -0.1700
Data Index: 8268127 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.9056. Min Act: -0.1700
Data Index: 6383840 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.8119. Min Act: -0.1700
Data Index: 2494258 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.7494. Min Act: -0.1700
Data Index: 8730155 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.7806. Min Act: -0.1700
Data Index: 2732207 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.6556. Min Act: -0.1700
Data Index: 4382210 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.6244. Min Act: -0.1700
Data Index: 2008598 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.6244. Min Act: -0.1700
Data Index: 2967817 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.6244. Min Act: -0.1700
Data Index: 6080954 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5619. Min Act: -0.1700
Data Index: 7015135 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5619. Min Act: -0.1700
Data Index: 5029163 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5619. Min Act: -0.1700
Data Index: 4431261 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5619. Min Act: -0.1700
Data Index: 2412646 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5931. Min Act: -0.1700
Data Index: 3703301 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5306. Min Act: -0.1700
Data Index: 5004627 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.5306. Min Act: -0.1700
Data Index: 5205609 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2494. Min Range: -8.2494
Max Act: 7.4994. Min Act: -0.1700
Data Index: 1859435 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19