Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4393 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0424. Min Range: -6.0424
Max Act: 6.0424. Min Act: -0.1700
Data Index: 2081071 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0424. Min Range: -6.0424
Max Act: 6.0424. Min Act: -0.1700
Data Index: 7756782 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.9174. Min Act: -0.1700
Data Index: 4733721 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.8861. Min Act: -0.1700
Data Index: 8228326 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.8549. Min Act: -0.1700
Data Index: 4671993 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.8236. Min Act: -0.1700
Data Index: 3675155 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.7924. Min Act: -0.1700
Data Index: 4361820 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.7611. Min Act: -0.1700
Data Index: 571748 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.7611. Min Act: -0.1700
Data Index: 2081059 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.7299. Min Act: -0.1700
Data Index: 8100042 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.7611. Min Act: -0.1700
Data Index: 2235035 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 845849 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 6719575 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 4435231 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 983224 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6361. Min Act: -0.1700
Data Index: 6530038 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6674. Min Act: -0.1700
Data Index: 3169246 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 8364567 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6674. Min Act: -0.1700
Data Index: 5014498 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0424. Min Range: -6.0424
Max Act: 5.6986. Min Act: -0.1700
Data Index: 3169248 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19