Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4232 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.4769. Min Act: -0.1700
Data Index: 4730812 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.4144. Min Act: -0.1700
Data Index: 8229218 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.3831. Min Act: -0.1700
Data Index: 8440791 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.1644. Min Act: -0.1700
Data Index: 5769048 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.1331. Min Act: -0.1700
Data Index: 2415720 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.1331. Min Act: -0.1700
Data Index: 2580240 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0393. Min Act: -0.1700
Data Index: 7386242 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0706. Min Act: -0.1700
Data Index: 2608796 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0706. Min Act: -0.1700
Data Index: 4053822 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0393. Min Act: -0.1700
Data Index: 1772271 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0081. Min Act: -0.1700
Data Index: 569309 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0081. Min Act: -0.1700
Data Index: 954236 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9768. Min Act: -0.1700
Data Index: 8744096 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0081. Min Act: -0.1700
Data Index: 4888784 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4769. Min Range: -4.4769
Max Act: 4.0081. Min Act: -0.1700
Data Index: 5194229 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9768. Min Act: -0.1700
Data Index: 5526491 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9456. Min Act: -0.1700
Data Index: 5250939 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9768. Min Act: -0.1700
Data Index: 5286061 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9143. Min Act: -0.1700
Data Index: 1565446 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4769. Min Range: -4.4769
Max Act: 3.9143. Min Act: -0.1700
Data Index: 1013994 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19