Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.7505. Min Act: -0.1700
Data Index: 6092446 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.7193. Min Act: -0.1700
Data Index: 1973690 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.5943. Min Act: -0.1700
Data Index: 3525338 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.4068. Min Act: -0.1700
Data Index: 3726466 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.3443. Min Act: -0.1700
Data Index: 1101220 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.3443. Min Act: -0.1700
Data Index: 102188 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7505. Min Range: -7.7505
Max Act: 7.0005. Min Act: -0.1700
Data Index: 3327313 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.8755. Min Act: -0.1700
Data Index: 1768558 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.8130. Min Act: -0.1700
Data Index: 1947933 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7818. Min Act: -0.1700
Data Index: 1621317 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7818. Min Act: -0.1700
Data Index: 7091273 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7505. Min Act: -0.1700
Data Index: 3812193 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7505. Min Act: -0.1700
Data Index: 8168785 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7193. Min Act: -0.1700
Data Index: 5669653 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7193. Min Act: -0.1700
Data Index: 3726465 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.7193. Min Act: -0.1700
Data Index: 5161493 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.6880. Min Act: -0.1700
Data Index: 1082516 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.6568. Min Act: -0.1700
Data Index: 4003118 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.6880. Min Act: -0.1700
Data Index: 5967667 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7505. Min Range: -7.7505
Max Act: 6.6255. Min Act: -0.1700
Data Index: 51750 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19