Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0215. Min Range: -6.0215
Max Act: 6.0215. Min Act: -0.1700
Data Index: 5042891 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.8028. Min Act: -0.1700
Data Index: 6461454 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.7090. Min Act: -0.1700
Data Index: 1252808 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6778. Min Act: -0.1700
Data Index: 807032 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6778. Min Act: -0.1700
Data Index: 8075224 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 3281413 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6778. Min Act: -0.1700
Data Index: 8800397 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 6140488 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 8056311 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5592923 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6778. Min Act: -0.1700
Data Index: 8383763 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6778. Min Act: -0.1700
Data Index: 432033 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 1490618 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6465. Min Act: -0.1700
Data Index: 7852725 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6153. Min Act: -0.1700
Data Index: 6013341 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5719013 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.6153. Min Act: -0.1700
Data Index: 7394786 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.5840. Min Act: -0.1700
Data Index: 3173745 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.5840. Min Act: -0.1700
Data Index: 8012861 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0215. Min Range: -6.0215
Max Act: 5.5840. Min Act: -0.1700
Data Index: 4980756 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19