Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4367. Min Range: -10.4367
Max Act: 10.4367. Min Act: -0.1700
Data Index: 6778167 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4367. Min Range: -10.4367
Max Act: 10.3742. Min Act: -0.1700
Data Index: 7784568 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4367. Min Range: -10.4367
Max Act: 10.2492. Min Act: -0.1700
Data Index: 4069994 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4367. Min Range: -10.4367
Max Act: 10.1242. Min Act: -0.1700
Data Index: 2775192 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4367. Min Range: -10.4367
Max Act: 10.0617. Min Act: -0.1700
Data Index: 7857290 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.9992. Min Act: -0.1700
Data Index: 6059867 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.9367. Min Act: -0.1700
Data Index: 4427242 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.9367. Min Act: -0.1700
Data Index: 1350572 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.9367. Min Act: -0.1700
Data Index: 4343833 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.9367. Min Act: -0.1700
Data Index: 1355958 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8742. Min Act: -0.1700
Data Index: 4065776 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8742. Min Act: -0.1700
Data Index: 801613 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 6604406 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8742. Min Act: -0.1700
Data Index: 6565654 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8742. Min Act: -0.1700
Data Index: 2882770 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 7019679 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 4500538 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 5914842 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 7851865 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4367. Min Range: -10.4367
Max Act: 9.8117. Min Act: -0.1700
Data Index: 4631777 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19