Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0435. Min Range: -8.0435
Max Act: 8.0435. Min Act: -0.1700
Data Index: 5739909 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.9810. Min Act: -0.1700
Data Index: 7630167 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.9810. Min Act: -0.1700
Data Index: 6481665 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.8248. Min Act: -0.1700
Data Index: 5262577 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.8560. Min Act: -0.1700
Data Index: 7047446 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.8248. Min Act: -0.1700
Data Index: 5632664 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.8248. Min Act: -0.1700
Data Index: 4809780 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.8248. Min Act: -0.1700
Data Index: 288445 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.7623. Min Act: -0.1700
Data Index: 6441546 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.7310. Min Act: -0.1700
Data Index: 6069914 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.6998. Min Act: -0.1700
Data Index: 8704520 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.6373. Min Act: -0.1700
Data Index: 6054150 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5748. Min Act: -0.1700
Data Index: 6294773 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5748. Min Act: -0.1700
Data Index: 4923112 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5435. Min Act: -0.1700
Data Index: 8147709 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5435. Min Act: -0.1700
Data Index: 7499017 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5123. Min Act: -0.1700
Data Index: 3576641 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5123. Min Act: -0.1700
Data Index: 1942477 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.5123. Min Act: -0.1700
Data Index: 6096599 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0435. Min Range: -8.0435
Max Act: 7.4810. Min Act: -0.1700
Data Index: 8425812 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19