Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.7540. Min Act: -0.1700
Data Index: 3448046 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.6290. Min Act: -0.1700
Data Index: 6340844 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.5040. Min Act: -0.1700
Data Index: 1018204 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.3477. Min Act: -0.1700
Data Index: 7213506 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.2540. Min Act: -0.1700
Data Index: 7299419 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.0977. Min Act: -0.1700
Data Index: 6594248 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.0665. Min Act: -0.1700
Data Index: 2014092 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.0665. Min Act: -0.1700
Data Index: 5572746 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.0665. Min Act: -0.1700
Data Index: 764881 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7540. Min Range: -7.7540
Max Act: 7.0352. Min Act: -0.1700
Data Index: 1373338 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9727. Min Act: -0.1700
Data Index: 7298960 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9727. Min Act: -0.1700
Data Index: 2365020 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9102. Min Act: -0.1700
Data Index: 7972090 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9102. Min Act: -0.1700
Data Index: 5634213 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9102. Min Act: -0.1700
Data Index: 7787014 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.9102. Min Act: -0.1700
Data Index: 1789160 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.8477. Min Act: -0.1700
Data Index: 3448047 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.8790. Min Act: -0.1700
Data Index: 6864800 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.8165. Min Act: -0.1700
Data Index: 4683825 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7540. Min Range: -7.7540
Max Act: 6.8165. Min Act: -0.1700
Data Index: 4847066 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19