Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.3294. Min Act: -0.1700
Data Index: 6794346 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.2982. Min Act: -0.1700
Data Index: 131156 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.2357. Min Act: -0.1700
Data Index: 2462699 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.1419. Min Act: -0.1700
Data Index: 2297862 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7912754 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.1419. Min Act: -0.1700
Data Index: 2339741 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.1732. Min Act: -0.1700
Data Index: 7786853 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3294. Min Range: -7.3294
Max Act: 7.0169. Min Act: -0.1700
Data Index: 5002124 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6754430 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.9544. Min Act: -0.1700
Data Index: 4816573 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.9544. Min Act: -0.1700
Data Index: 4699732 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.9232. Min Act: -0.1700
Data Index: 3923832 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.9232. Min Act: -0.1700
Data Index: 6243969 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8607. Min Act: -0.1700
Data Index: 15312 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 6780024 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 7639155 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 8523718 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 4770957 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 5041884 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3294. Min Range: -7.3294
Max Act: 6.7982. Min Act: -0.1700
Data Index: 2834845 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19