Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.7002. Min Act: -0.1700
Data Index: 4983474 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.6377. Min Act: -0.1700
Data Index: 227965 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.5752. Min Act: -0.1700
Data Index: 3880298 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.5127. Min Act: -0.1700
Data Index: 8259699 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.5127. Min Act: -0.1700
Data Index: 7912389 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 6696584 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.4815. Min Act: -0.1700
Data Index: 1324349 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.3877. Min Act: -0.1700
Data Index: 5994939 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 2930907 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.4190. Min Act: -0.1700
Data Index: 6955383 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.2940. Min Act: -0.1700
Data Index: 6173035 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2810752 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7589360 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1690. Min Act: -0.1700
Data Index: 3242812 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.2002. Min Act: -0.1700
Data Index: 3490134 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1690. Min Act: -0.1700
Data Index: 8258584 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1690. Min Act: -0.1700
Data Index: 4979316 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1690. Min Act: -0.1700
Data Index: 8809424 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1377. Min Act: -0.1700
Data Index: 8546989 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7002. Min Range: -7.7002
Max Act: 7.1377. Min Act: -0.1700
Data Index: 8595004 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19