Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0978. Min Range: -11.0978
Max Act: 11.0978. Min Act: -0.1690
Data Index: 2235737 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.9103. Min Act: -0.1674
Data Index: 5639403 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.6603. Min Act: -0.1699
Data Index: 7380892 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.5353. Min Act: -0.1665
Data Index: 4894899 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.4728. Min Act: -0.1700
Data Index: 3050116 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.3478. Min Act: -0.1676
Data Index: 5688620 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2853. Min Act: -0.1700
Data Index: 3465424 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2853. Min Act: -0.1690
Data Index: 3488500 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2228. Min Act: -0.1699
Data Index: 8115641 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2228. Min Act: -0.1700
Data Index: 2082322 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2228. Min Act: -0.1647
Data Index: 8533142 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.1603. Min Act: -0.1692
Data Index: 5584185 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.2228. Min Act: -0.1690
Data Index: 2033301 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.0978. Min Act: -0.1700
Data Index: 2697721 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.0978. Min Act: -0.1700
Data Index: 4321330 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0978. Min Range: -11.0978
Max Act: 10.0978. Min Act: -0.1700
Data Index: 6796033 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0978. Min Range: -11.0978
Max Act: 9.9728. Min Act: -0.1696
Data Index: 5345881 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0978. Min Range: -11.0978
Max Act: 9.9728. Min Act: -0.1700
Data Index: 7007851 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0978. Min Range: -11.0978
Max Act: 9.9728. Min Act: -0.1700
Data Index: 7037989 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0978. Min Range: -11.0978
Max Act: 9.9728. Min Act: -0.1700
Data Index: 6596890 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19