Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3986. Min Range: -9.3986
Max Act: 9.3986. Min Act: -0.1700
Data Index: 1393768 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.6486. Min Act: -0.1700
Data Index: 2756862 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.6486. Min Act: -0.1700
Data Index: 8067335 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.6486. Min Act: -0.1700
Data Index: 8523661 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.5861. Min Act: -0.1700
Data Index: 1052000 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.5236. Min Act: -0.1700
Data Index: 1854711 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.5236. Min Act: -0.1700
Data Index: 8654299 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3986. Min Act: -0.1700
Data Index: 3352546 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3361. Min Act: -0.1700
Data Index: 6091001 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3986. Min Act: -0.1700
Data Index: 4226424 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3986. Min Act: -0.1700
Data Index: 3352544 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3361. Min Act: -0.1700
Data Index: 5346370 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3986. Min Act: -0.1700
Data Index: 8354178 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3361. Min Act: -0.1700
Data Index: 2793357 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.3361. Min Act: -0.1700
Data Index: 8069171 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.2736. Min Act: -0.1700
Data Index: 6736331 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.2423. Min Act: -0.1700
Data Index: 5977247 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.2111. Min Act: -0.1700
Data Index: 8590410 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.1798. Min Act: -0.1700
Data Index: 666096 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3986. Min Range: -9.3986
Max Act: 8.2111. Min Act: -0.1700
Data Index: 6824930 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19