Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.3781. Min Act: -0.1700
Data Index: 5076783 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.3469. Min Act: -0.1700
Data Index: 7360239 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.2844. Min Act: -0.1700
Data Index: 4960590 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.1906. Min Act: -0.1700
Data Index: 5132111 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.1281. Min Act: -0.1700
Data Index: 5239138 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0969. Min Act: -0.1700
Data Index: 3304678 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0344. Min Act: -0.1700
Data Index: 882677 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0344. Min Act: -0.1700
Data Index: 2151876 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 3745608 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 367183 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0344. Min Act: -0.1700
Data Index: 4974353 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3781. Min Range: -6.3781
Max Act: 5.9719. Min Act: -0.1700
Data Index: 2338271 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 7594446 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 75425 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 2084710 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 7501812 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 3611436 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 7023484 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3781. Min Range: -6.3781
Max Act: 6.0031. Min Act: -0.1700
Data Index: 6963104 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3781. Min Range: -6.3781
Max Act: 5.9719. Min Act: -0.1700
Data Index: 5113866 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19