Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7078627 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5914. Min Act: -0.1700
Data Index: 3181879 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5914. Min Act: -0.1700
Data Index: 584275 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5914. Min Act: -0.1700
Data Index: 5824193 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 944789 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 5390140 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 874305 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 8432340 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 5081525 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 922334 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 429881 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4648383 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4071246 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3898379 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3208504 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 975387 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2154354 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 2334952 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 579700 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6226. Min Range: -6.6226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 116323 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19