Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.1461. Min Act: -0.1700
Data Index: 4909420 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.1774. Min Act: -0.1700
Data Index: 589789 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3706602 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4566431 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 8232291 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 3048273 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4765120 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 1487421 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 7564970 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 6475456 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0836. Min Act: -0.1700
Data Index: 7499767 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 5730538 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 8232308 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 6729124 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 8281405 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 4566442 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 6506087 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0211. Min Act: -0.1700
Data Index: 2214839 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0524. Min Act: -0.1700
Data Index: 3480828 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1774. Min Range: -5.1774
Max Act: 5.0211. Min Act: -0.1700
Data Index: 2814906 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19