Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5797. Min Range: -6.5797
Max Act: 6.5797. Min Act: -0.1700
Data Index: 4826920 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.8922. Min Act: -0.1700
Data Index: 2250311 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.8297. Min Act: -0.1700
Data Index: 6042821 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.7984. Min Act: -0.1700
Data Index: 2220192 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.7672. Min Act: -0.1700
Data Index: 3228613 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.7047. Min Act: -0.1700
Data Index: 1127440 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.7047. Min Act: -0.1700
Data Index: 4342420 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.7359. Min Act: -0.1700
Data Index: 3651751 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 5983665 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.6734. Min Act: -0.1700
Data Index: 5573864 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 7750938 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.6109. Min Act: -0.1700
Data Index: 1331588 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5797. Min Act: -0.1700
Data Index: 7959044 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5797. Min Act: -0.1700
Data Index: 6797226 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5484. Min Act: -0.1700
Data Index: 2578336 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5484. Min Act: -0.1700
Data Index: 3482738 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5484. Min Act: -0.1700
Data Index: 5408306 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5172. Min Act: -0.1700
Data Index: 2304508 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5172. Min Act: -0.1700
Data Index: 1573160 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5797. Min Range: -6.5797
Max Act: 5.5172. Min Act: -0.1700
Data Index: 8628101 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19