Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.8877. Min Act: -0.1700
Data Index: 4809154 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.5127. Min Act: -0.1700
Data Index: 4368045 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.4190. Min Act: -0.1700
Data Index: 2387183 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.2940. Min Act: -0.1700
Data Index: 7332223 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.2002. Min Act: -0.1700
Data Index: 8184092 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.1690. Min Act: -0.1700
Data Index: 6317117 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.1377. Min Act: -0.1700
Data Index: 3460439 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.1065. Min Act: -0.1700
Data Index: 3195483 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8877. Min Range: -7.8877
Max Act: 7.0127. Min Act: -0.1700
Data Index: 7171278 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.9815. Min Act: -0.1700
Data Index: 3815580 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.9190. Min Act: -0.1700
Data Index: 5921331 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.9190. Min Act: -0.1700
Data Index: 3078281 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.8565. Min Act: -0.1700
Data Index: 5381876 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.8252. Min Act: -0.1700
Data Index: 121760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.8565. Min Act: -0.1700
Data Index: 2262045 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.7940. Min Act: -0.1700
Data Index: 4426935 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5005501 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.8252. Min Act: -0.1700
Data Index: 6547087 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.7940. Min Act: -0.1700
Data Index: 8561063 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8877. Min Range: -7.8877
Max Act: 6.7940. Min Act: -0.1700
Data Index: 6305706 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19