Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4512 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0910. Min Range: -8.0910
Max Act: 8.0910. Min Act: -0.1700
Data Index: 8642837 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0910. Min Range: -8.0910
Max Act: 8.0910. Min Act: -0.1700
Data Index: 8642828 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0910. Min Range: -8.0910
Max Act: 8.0285. Min Act: -0.1700
Data Index: 7872482 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.9348. Min Act: -0.1700
Data Index: 2879812 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.9348. Min Act: -0.1700
Data Index: 4538857 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.8723. Min Act: -0.1700
Data Index: 3656340 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.8098. Min Act: -0.1700
Data Index: 5382981 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.8098. Min Act: -0.1700
Data Index: 2073746 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.8098. Min Act: -0.1700
Data Index: 8251308 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.8098. Min Act: -0.1700
Data Index: 8448756 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.7785. Min Act: -0.1700
Data Index: 7379783 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.6848. Min Act: -0.1700
Data Index: 7379778 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.7160. Min Act: -0.1700
Data Index: 2073748 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.7160. Min Act: -0.1700
Data Index: 4713513 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.6535. Min Act: -0.1700
Data Index: 5382979 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.6535. Min Act: -0.1700
Data Index: 5475838 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.6535. Min Act: -0.1700
Data Index: 2849294 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.6223. Min Act: -0.1700
Data Index: 4930837 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.5910. Min Act: -0.1700
Data Index: 8642831 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0910. Min Range: -8.0910
Max Act: 7.5910. Min Act: -0.1700
Data Index: 1748889 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19