Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5161 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9811. Min Act: -0.1700
Data Index: 409946 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9811. Min Act: -0.1700
Data Index: 1858788 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9499. Min Act: -0.1700
Data Index: 409930 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9499. Min Act: -0.1700
Data Index: 4859878 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 409932 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 5241631 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 1780793 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 7062729 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 409945 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.9186. Min Act: -0.1700
Data Index: 4688670 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 8358057 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 1116220 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 4515402 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 2401764 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 2526981 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 4252995 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 2613548 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8873. Min Act: -0.1700
Data Index: 4859882 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8561. Min Act: -0.1700
Data Index: 862082 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9811. Min Range: -3.9811
Max Act: 3.8561. Min Act: -0.1700
Data Index: 791578 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19