Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.9015. Min Act: -0.1700
Data Index: 470589 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.9015. Min Act: -0.1700
Data Index: 892894 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.8077. Min Act: -0.1700
Data Index: 7472782 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7765. Min Act: -0.1700
Data Index: 1431165 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7452. Min Act: -0.1700
Data Index: 3516619 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7140. Min Act: -0.1700
Data Index: 4492566 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7140. Min Act: -0.1700
Data Index: 3101911 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7140. Min Act: -0.1700
Data Index: 1665190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7140. Min Act: -0.1700
Data Index: 7633442 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.7140. Min Act: -0.1700
Data Index: 5678904 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5727188 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6827. Min Act: -0.1700
Data Index: 7521614 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6515. Min Act: -0.1700
Data Index: 8587877 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6827. Min Act: -0.1700
Data Index: 6521096 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6202. Min Act: -0.1700
Data Index: 2878716 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6749254 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6515. Min Act: -0.1700
Data Index: 3529372 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6515. Min Act: -0.1700
Data Index: 1938125 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6202. Min Act: -0.1700
Data Index: 515582 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9015. Min Range: -5.9015
Max Act: 5.6202. Min Act: -0.1700
Data Index: 5417772 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19