Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5747 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.4594. Min Act: -0.1700
Data Index: 1995735 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.2406. Min Act: -0.1700
Data Index: 7734850 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.1781. Min Act: -0.1700
Data Index: 8129894 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.1156. Min Act: -0.1700
Data Index: 6451390 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.1156. Min Act: -0.1700
Data Index: 1988262 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0844. Min Act: -0.1700
Data Index: 326294 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.1156. Min Act: -0.1700
Data Index: 2289208 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.1156. Min Act: -0.1700
Data Index: 6339522 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0844. Min Act: -0.1700
Data Index: 2156544 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0844. Min Act: -0.1700
Data Index: 5948088 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0531. Min Act: -0.1700
Data Index: 7166072 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0844. Min Act: -0.1700
Data Index: 8759100 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0219. Min Act: -0.1700
Data Index: 7308125 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2043012 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2720829 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0531. Min Act: -0.1700
Data Index: 8352868 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4594. Min Range: -6.4594
Max Act: 5.9906. Min Act: -0.1700
Data Index: 8221654 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0219. Min Act: -0.1700
Data Index: 5760174 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0531. Min Act: -0.1700
Data Index: 171715 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4594. Min Range: -6.4594
Max Act: 6.0219. Min Act: -0.1700
Data Index: 4249014 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19