Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2313 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.5176. Min Act: -0.1700
Data Index: 6716829 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.4551. Min Act: -0.1700
Data Index: 1341117 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.3926. Min Act: -0.1700
Data Index: 591991 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.3301. Min Act: -0.1700
Data Index: 5049824 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.3926. Min Act: -0.1700
Data Index: 7665783 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.3926. Min Act: -0.1700
Data Index: 8699949 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.2676. Min Act: -0.1700
Data Index: 6714775 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.2676. Min Act: -0.1700
Data Index: 6798217 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.2051. Min Act: -0.1700
Data Index: 4490177 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.1426. Min Act: -0.1700
Data Index: 1868320 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.1426. Min Act: -0.1700
Data Index: 6020066 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.1426. Min Act: -0.1700
Data Index: 2417482 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0801. Min Act: -0.1700
Data Index: 4791758 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0176. Min Act: -0.1700
Data Index: 4236523 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0801. Min Act: -0.1700
Data Index: 6941679 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0801. Min Act: -0.1700
Data Index: 5371835 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0801. Min Act: -0.1700
Data Index: 153919 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5176. Min Range: -9.5176
Max Act: 8.9551. Min Act: -0.1700
Data Index: 4791762 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0801. Min Act: -0.1700
Data Index: 7128657 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5176. Min Range: -9.5176
Max Act: 9.0176. Min Act: -0.1700
Data Index: 8493109 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19