Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.4029. Min Act: -0.1700
Data Index: 875325 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.5279. Min Act: -0.1700
Data Index: 5628856 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.2779. Min Act: -0.1700
Data Index: 6747825 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.3404. Min Act: -0.1700
Data Index: 5788269 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.2779. Min Act: -0.1700
Data Index: 4781294 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.2779. Min Act: -0.1700
Data Index: 4623622 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.2154. Min Act: -0.1700
Data Index: 7052392 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.2779. Min Act: -0.1700
Data Index: 7245372 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 8765357 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 2316983 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.0904. Min Act: -0.1700
Data Index: 5076525 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 8765341 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 8560825 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 5720393 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 5153879 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 8008151 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 7495744 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 3504387 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.1529. Min Act: -0.1700
Data Index: 5179903 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5279. Min Range: -9.5279
Max Act: 9.0904. Min Act: -0.1700
Data Index: 856189 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19