Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.1536. Min Act: -0.1700
Data Index: 7475861 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.1536. Min Act: -0.1700
Data Index: 8580984 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0911. Min Act: -0.1700
Data Index: 3998721 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0286. Min Act: -0.1700
Data Index: 8780997 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0286. Min Act: -0.1700
Data Index: 2377147 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0911. Min Act: -0.1700
Data Index: 1179895 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0286. Min Act: -0.1700
Data Index: 4891968 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0286. Min Act: -0.1700
Data Index: 3958061 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1536. Min Range: -9.1536
Max Act: 9.0286. Min Act: -0.1700
Data Index: 863997 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9661. Min Act: -0.1700
Data Index: 980649 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9661. Min Act: -0.1700
Data Index: 4671124 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9661. Min Act: -0.1700
Data Index: 8690232 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9661. Min Act: -0.1700
Data Index: 6007780 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9661. Min Act: -0.1700
Data Index: 1626887 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9036. Min Act: -0.1700
Data Index: 3850710 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9036. Min Act: -0.1700
Data Index: 5366256 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.8411. Min Act: -0.1700
Data Index: 8627673 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9036. Min Act: -0.1700
Data Index: 5742233 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9036. Min Act: -0.1700
Data Index: 5553943 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1536. Min Range: -9.1536
Max Act: 8.9036. Min Act: -0.1700
Data Index: 7330814 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19