Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 310 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4918. Min Range: -8.4918
Max Act: 8.4918. Min Act: -0.1700
Data Index: 8484108 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.9918. Min Act: -0.1700
Data Index: 8414470 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.7418. Min Act: -0.1700
Data Index: 3389573 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.6793. Min Act: -0.1700
Data Index: 1739834 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.5231. Min Act: -0.1700
Data Index: 2229090 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.4606. Min Act: -0.1700
Data Index: 7655362 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.3043. Min Act: -0.1700
Data Index: 1799919 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.3043. Min Act: -0.1700
Data Index: 406825 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.3043. Min Act: -0.1700
Data Index: 6860797 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.2418. Min Act: -0.1700
Data Index: 7222916 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.2418. Min Act: -0.1700
Data Index: 4729886 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.2418. Min Act: -0.1700
Data Index: 3520792 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1793. Min Act: -0.1700
Data Index: 2161857 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1481. Min Act: -0.1700
Data Index: 5546847 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1168. Min Act: -0.1700
Data Index: 8147683 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1481. Min Act: -0.1700
Data Index: 3846600 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1168. Min Act: -0.1700
Data Index: 43273 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1168. Min Act: -0.1700
Data Index: 5508192 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.1168. Min Act: -0.1700
Data Index: 8417794 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4918. Min Range: -8.4918
Max Act: 7.0856. Min Act: -0.1700
Data Index: 1734979 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19