Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6015 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2478. Min Range: -9.2478
Max Act: 9.2478. Min Act: -0.1700
Data Index: 4245201 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.8103. Min Act: -0.1700
Data Index: 242170 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.8103. Min Act: -0.1700
Data Index: 6038017 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.8103. Min Act: -0.1700
Data Index: 2264798 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.8103. Min Act: -0.1700
Data Index: 8711498 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.7478. Min Act: -0.1700
Data Index: 2821863 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.7478. Min Act: -0.1700
Data Index: 7354660 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6853. Min Act: -0.1700
Data Index: 6152453 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6853. Min Act: -0.1700
Data Index: 3212889 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6853. Min Act: -0.1700
Data Index: 723581 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6853. Min Act: -0.1700
Data Index: 3846745 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6228. Min Act: -0.1700
Data Index: 845129 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6228. Min Act: -0.1700
Data Index: 5369503 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.5603. Min Act: -0.1700
Data Index: 2233489 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.5603. Min Act: -0.1700
Data Index: 203792 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.5603. Min Act: -0.1700
Data Index: 5683055 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.6228. Min Act: -0.1700
Data Index: 160369 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.5603. Min Act: -0.1700
Data Index: 6583518 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.5603. Min Act: -0.1700
Data Index: 3078272 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2478. Min Range: -9.2478
Max Act: 8.4978. Min Act: -0.1700
Data Index: 4161937 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19