Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.6820. Min Act: -0.1700
Data Index: 1790875 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.5882. Min Act: -0.1700
Data Index: 2687825 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.5570. Min Act: -0.1700
Data Index: 6420927 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2687827 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2302907 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.4007. Min Act: -0.1700
Data Index: 7548275 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3773022 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.3382. Min Act: -0.1700
Data Index: 1874944 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.2757. Min Act: -0.1700
Data Index: 1847381 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.2445. Min Act: -0.1700
Data Index: 7156732 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.2132. Min Act: -0.1700
Data Index: 2543127 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.2132. Min Act: -0.1700
Data Index: 7813439 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1820. Min Act: -0.1700
Data Index: 5995811 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7548272 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7383919 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7967561 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1507. Min Act: -0.1700
Data Index: 6301780 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1195. Min Act: -0.1700
Data Index: 909077 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.1195. Min Act: -0.1700
Data Index: 7312715 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6820. Min Range: -5.6820
Max Act: 5.0882. Min Act: -0.1700
Data Index: 7664857 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19