Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0900. Min Range: -8.0900
Max Act: 8.0900. Min Act: -0.1700
Data Index: 6979808 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.9025. Min Act: -0.1700
Data Index: 3933353 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.9025. Min Act: -0.1700
Data Index: 3184908 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.8400. Min Act: -0.1700
Data Index: 1442372 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.8400. Min Act: -0.1700
Data Index: 7301425 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.8400. Min Act: -0.1700
Data Index: 639342 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.8400. Min Act: -0.1700
Data Index: 7530280 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7775. Min Act: -0.1700
Data Index: 2054186 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7775. Min Act: -0.1700
Data Index: 6612584 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7775. Min Act: -0.1700
Data Index: 3162486 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7150. Min Act: -0.1700
Data Index: 7109027 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7150. Min Act: -0.1700
Data Index: 1882132 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7150. Min Act: -0.1700
Data Index: 1959412 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.7150. Min Act: -0.1700
Data Index: 8312310 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.6525. Min Act: -0.1700
Data Index: 5920192 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.6525. Min Act: -0.1700
Data Index: 7602565 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.6525. Min Act: -0.1700
Data Index: 4201321 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.6525. Min Act: -0.1700
Data Index: 4601497 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.6525. Min Act: -0.1700
Data Index: 8091125 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0900. Min Range: -8.0900
Max Act: 7.5900. Min Act: -0.1700
Data Index: 6991951 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19