Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2562. Min Range: -8.2562
Max Act: 8.2562. Min Act: -0.1699
Data Index: 1944882 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2562. Min Range: -8.2562
Max Act: 8.1312. Min Act: -0.1700
Data Index: 8079702 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2562. Min Range: -8.2562
Max Act: 8.0062. Min Act: -0.1700
Data Index: 5277398 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.8812. Min Act: -0.1700
Data Index: 1979526 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.8187. Min Act: -0.1700
Data Index: 8079705 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.8187. Min Act: -0.1700
Data Index: 5382981 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.7562. Min Act: -0.1700
Data Index: 3931951 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.7562. Min Act: -0.1700
Data Index: 1792586 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.7562. Min Act: -0.1700
Data Index: 7256698 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6937. Min Act: -0.1700
Data Index: 3575411 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 8011527 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 106827 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 5967038 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 5945398 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 4003718 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.5687. Min Act: -0.1700
Data Index: 7341696 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.6312. Min Act: -0.1700
Data Index: 3835401 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.5687. Min Act: -0.1700
Data Index: 4076143 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.5062. Min Act: -0.1700
Data Index: 1256508 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2562. Min Range: -8.2562
Max Act: 7.5062. Min Act: -0.1700
Data Index: 3137111 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19