Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.3170. Min Act: -0.1700
Data Index: 2952211 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.2858. Min Act: -0.1700
Data Index: 5176258 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.2858. Min Act: -0.1700
Data Index: 4695706 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.2233. Min Act: -0.1700
Data Index: 550465 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.2233. Min Act: -0.1700
Data Index: 4737978 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1920. Min Act: -0.1700
Data Index: 673391 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1608. Min Act: -0.1700
Data Index: 1924594 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1608. Min Act: -0.1700
Data Index: 7717281 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1608. Min Act: -0.1700
Data Index: 8025480 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1608. Min Act: -0.1700
Data Index: 1924593 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1608. Min Act: -0.1700
Data Index: 1874613 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.1295. Min Act: -0.1700
Data Index: 7299605 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0983. Min Act: -0.1700
Data Index: 8475456 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0983. Min Act: -0.1700
Data Index: 7717279 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0670. Min Act: -0.1700
Data Index: 3897616 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0983. Min Act: -0.1700
Data Index: 3199041 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5449415 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0670. Min Act: -0.1700
Data Index: 602210 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0670. Min Act: -0.1700
Data Index: 3619553 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3170. Min Range: -6.3170
Max Act: 6.0670. Min Act: -0.1700
Data Index: 6255249 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19