Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2665. Min Range: -7.2665
Max Act: 7.2665. Min Act: -0.1700
Data Index: 7663555 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2665. Min Range: -7.2665
Max Act: 7.1727. Min Act: -0.1700
Data Index: 4409062 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.9227. Min Act: -0.1700
Data Index: 4704294 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8915. Min Act: -0.1700
Data Index: 6014443 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8915. Min Act: -0.1700
Data Index: 4379838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8602. Min Act: -0.1700
Data Index: 6137677 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8290. Min Act: -0.1700
Data Index: 903513 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8290. Min Act: -0.1700
Data Index: 8787621 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8290. Min Act: -0.1700
Data Index: 2940352 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8290. Min Act: -0.1700
Data Index: 5218215 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.8290. Min Act: -0.1700
Data Index: 187215 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7977. Min Act: -0.1700
Data Index: 3119745 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7665. Min Act: -0.1700
Data Index: 6674827 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7352. Min Act: -0.1700
Data Index: 3604354 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7040. Min Act: -0.1700
Data Index: 5975514 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7040. Min Act: -0.1700
Data Index: 982422 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.7040. Min Act: -0.1700
Data Index: 4100181 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.6727. Min Act: -0.1700
Data Index: 2267712 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.6727. Min Act: -0.1700
Data Index: 7279869 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2665. Min Range: -7.2665
Max Act: 6.6727. Min Act: -0.1700
Data Index: 5789658 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19