Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.4682. Min Act: -0.1700
Data Index: 6869631 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.3432. Min Act: -0.1700
Data Index: 2609148 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.2495. Min Act: -0.1700
Data Index: 1573194 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.2182. Min Act: -0.1700
Data Index: 7490684 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.1870. Min Act: -0.1700
Data Index: 6871654 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.1245. Min Act: -0.1700
Data Index: 896524 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0932. Min Act: -0.1700
Data Index: 3751132 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0620. Min Act: -0.1700
Data Index: 4517487 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0620. Min Act: -0.1700
Data Index: 47617 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2120099 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0307. Min Act: -0.1700
Data Index: 8536793 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4682. Min Range: -6.4682
Max Act: 6.0307. Min Act: -0.1700
Data Index: 6419125 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9682. Min Act: -0.1700
Data Index: 1080725 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 2460440 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4181873 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 7664223 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 8335299 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4821783 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.9057. Min Act: -0.1700
Data Index: 994289 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4682. Min Range: -6.4682
Max Act: 5.8432. Min Act: -0.1700
Data Index: 3831970 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19