Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.5367. Min Act: -0.1700
Data Index: 2660835 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.2242. Min Act: -0.1700
Data Index: 1797920 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.2242. Min Act: -0.1700
Data Index: 3076557 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0992. Min Act: -0.1700
Data Index: 7219989 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0367. Min Act: -0.1700
Data Index: 5553619 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0055. Min Act: -0.1700
Data Index: 3036473 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9742. Min Act: -0.1700
Data Index: 4075718 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0055. Min Act: -0.1700
Data Index: 6118619 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9430. Min Act: -0.1700
Data Index: 7538396 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9430. Min Act: -0.1700
Data Index: 4867594 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9742. Min Act: -0.1700
Data Index: 3732097 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8805. Min Act: -0.1700
Data Index: 1771746 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 8194945 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 2750149 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 985362 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7074064 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8805. Min Act: -0.1700
Data Index: 1546516 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8492. Min Act: -0.1700
Data Index: 4892896 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8805. Min Act: -0.1700
Data Index: 1979656 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8180. Min Act: -0.1700
Data Index: 4583789 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19