Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6790. Min Range: -9.6790
Max Act: 9.6790. Min Act: -0.1700
Data Index: 5892687 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6790. Min Range: -9.6790
Max Act: 9.3040. Min Act: -0.1700
Data Index: 5065223 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6790. Min Range: -9.6790
Max Act: 9.2415. Min Act: -0.1700
Data Index: 5573215 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.9915. Min Act: -0.1700
Data Index: 4831979 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.9290. Min Act: -0.1700
Data Index: 2538697 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.9290. Min Act: -0.1700
Data Index: 5912953 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.9290. Min Act: -0.1700
Data Index: 8822592 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.9290. Min Act: -0.1700
Data Index: 5122064 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8665. Min Act: -0.1700
Data Index: 8325510 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8665. Min Act: -0.1700
Data Index: 143422 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 6386393 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 1035049 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 8605705 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 7274514 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 752566 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.8040. Min Act: -0.1700
Data Index: 1619993 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.7415. Min Act: -0.1700
Data Index: 5990281 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.7415. Min Act: -0.1700
Data Index: 6272123 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.7415. Min Act: -0.1700
Data Index: 6341212 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6790. Min Range: -9.6790
Max Act: 8.6165. Min Act: -0.1700
Data Index: 4090172 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19