Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.4759. Min Act: -0.1700
Data Index: 3367961 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.4759. Min Act: -0.1700
Data Index: 5134843 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.3509. Min Act: -0.1700
Data Index: 1797562 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.3509. Min Act: -0.1700
Data Index: 2715454 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.2259. Min Act: -0.1700
Data Index: 652175 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.1634. Min Act: -0.1700
Data Index: 4317429 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.1634. Min Act: -0.1700
Data Index: 5408920 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.1634. Min Act: -0.1700
Data Index: 6235934 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.0384. Min Act: -0.1700
Data Index: 4690381 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.1009. Min Act: -0.1700
Data Index: 8443364 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.1009. Min Act: -0.1700
Data Index: 202349 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.0384. Min Act: -0.1700
Data Index: 413149 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.0384. Min Act: -0.1700
Data Index: 396214 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4759. Min Range: -8.4759
Max Act: 8.0384. Min Act: -0.1700
Data Index: 7125093 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.9134. Min Act: -0.1700
Data Index: 1824981 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.9134. Min Act: -0.1700
Data Index: 3951358 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.9134. Min Act: -0.1700
Data Index: 6579313 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.9134. Min Act: -0.1700
Data Index: 1339407 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.9134. Min Act: -0.1700
Data Index: 1803731 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4759. Min Range: -8.4759
Max Act: 7.8196. Min Act: -0.1700
Data Index: 5564904 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19