Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.5894. Min Act: -0.1700
Data Index: 31281 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.4644. Min Act: -0.1700
Data Index: 6754862 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.4644. Min Act: -0.1700
Data Index: 7781621 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.3394. Min Act: -0.1700
Data Index: 7875848 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.2769. Min Act: -0.1700
Data Index: 6928172 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.2769. Min Act: -0.1700
Data Index: 562046 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5894. Min Range: -9.5894
Max Act: 9.0894. Min Act: -0.1700
Data Index: 8270957 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.9019. Min Act: -0.1700
Data Index: 6097707 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.9019. Min Act: -0.1700
Data Index: 5728870 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.9019. Min Act: -0.1700
Data Index: 7051837 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.9019. Min Act: -0.1700
Data Index: 4127584 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.9019. Min Act: -0.1700
Data Index: 6844544 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.8394. Min Act: -0.1700
Data Index: 6529586 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.8394. Min Act: -0.1700
Data Index: 4620297 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.7769. Min Act: -0.1700
Data Index: 4516678 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.7769. Min Act: -0.1700
Data Index: 5555111 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.7144. Min Act: -0.1700
Data Index: 1447799 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.7769. Min Act: -0.1700
Data Index: 6029970 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.8394. Min Act: -0.1700
Data Index: 5831993 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5894. Min Range: -9.5894
Max Act: 8.7144. Min Act: -0.1700
Data Index: 7818683 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19