Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.9167. Min Act: -0.1700
Data Index: 1139263 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6677699 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.8229. Min Act: -0.1700
Data Index: 7437899 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7917. Min Act: -0.1700
Data Index: 599004 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7917. Min Act: -0.1700
Data Index: 5652300 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7917. Min Act: -0.1700
Data Index: 8631337 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7917. Min Act: -0.1700
Data Index: 7055325 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 2938492 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 5894664 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 1661024 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 5610065 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7292. Min Act: -0.1700
Data Index: 1309718 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7292. Min Act: -0.1700
Data Index: 8108135 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 1985158 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.7604. Min Act: -0.1700
Data Index: 1486677 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.6979. Min Act: -0.1700
Data Index: 3448639 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.6667. Min Act: -0.1700
Data Index: 1991017 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.6354. Min Act: -0.1700
Data Index: 1887967 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.6667. Min Act: -0.1700
Data Index: 48713 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9167. Min Range: -6.9167
Max Act: 6.6354. Min Act: -0.1700
Data Index: 7571733 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19