Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.3831. Min Act: -0.1700
Data Index: 4794270 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.2269. Min Act: -0.1700
Data Index: 7397237 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4714476 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8078230 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8672239 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0081. Min Act: -0.1700
Data Index: 8521639 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0081. Min Act: -0.1700
Data Index: 1817352 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0081. Min Act: -0.1700
Data Index: 6359772 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3831. Min Range: -5.3831
Max Act: 5.0081. Min Act: -0.1700
Data Index: 8416622 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9769. Min Act: -0.1700
Data Index: 1952751 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9144. Min Act: -0.1700
Data Index: 4134531 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9769. Min Act: -0.1700
Data Index: 6362822 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9144. Min Act: -0.1700
Data Index: 8376414 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9144. Min Act: -0.1700
Data Index: 1570158 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.8831. Min Act: -0.1700
Data Index: 8819488 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.8831. Min Act: -0.1700
Data Index: 4263653 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.8831. Min Act: -0.1700
Data Index: 1403078 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.8831. Min Act: -0.1700
Data Index: 5200722 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.9144. Min Act: -0.1700
Data Index: 7969029 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3831. Min Range: -5.3831
Max Act: 4.8831. Min Act: -0.1700
Data Index: 7155118 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19