Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.8849. Min Act: -0.1700
Data Index: 7000259 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.1974. Min Act: -0.1700
Data Index: 7826978 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.1349. Min Act: -0.1700
Data Index: 579106 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.1349. Min Act: -0.1700
Data Index: 5637724 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.1037. Min Act: -0.1700
Data Index: 2464033 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.0724. Min Act: -0.1700
Data Index: 6284062 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8849. Min Range: -8.8849
Max Act: 8.0099. Min Act: -0.1700
Data Index: 6258909 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.9162. Min Act: -0.1700
Data Index: 6261593 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.9474. Min Act: -0.1700
Data Index: 1642531 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.9162. Min Act: -0.1700
Data Index: 7079723 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8849. Min Act: -0.1700
Data Index: 530406 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8849. Min Act: -0.1700
Data Index: 5167059 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8849. Min Act: -0.1700
Data Index: 1607757 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8537. Min Act: -0.1700
Data Index: 3921021 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8224. Min Act: -0.1700
Data Index: 6397831 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8224. Min Act: -0.1700
Data Index: 6099571 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8224. Min Act: -0.1700
Data Index: 7298924 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8224. Min Act: -0.1700
Data Index: 8325659 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.8224. Min Act: -0.1700
Data Index: 6301554 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8849. Min Range: -8.8849
Max Act: 7.7912. Min Act: -0.1700
Data Index: 2922511 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19