Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6165 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2275. Min Range: -9.2275
Max Act: 9.2275. Min Act: -0.1700
Data Index: 7603981 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2275. Min Range: -9.2275
Max Act: 9.1650. Min Act: -0.1700
Data Index: 5540884 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2275. Min Range: -9.2275
Max Act: 9.1650. Min Act: -0.1700
Data Index: 4727850 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2275. Min Range: -9.2275
Max Act: 9.1025. Min Act: -0.1700
Data Index: 6514179 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.7900. Min Act: -0.1700
Data Index: 5784070 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.8525. Min Act: -0.1700
Data Index: 8353690 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.7275. Min Act: -0.1700
Data Index: 8069055 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.7275. Min Act: -0.1700
Data Index: 646413 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.6650. Min Act: -0.1700
Data Index: 4460589 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.6025. Min Act: -0.1700
Data Index: 1768105 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.5400. Min Act: -0.1700
Data Index: 5532476 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.5400. Min Act: -0.1700
Data Index: 6866989 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.4775. Min Act: -0.1700
Data Index: 3767768 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.4150. Min Act: -0.1700
Data Index: 1672498 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.4150. Min Act: -0.1700
Data Index: 4977174 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.4150. Min Act: -0.1700
Data Index: 481018 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.3525. Min Act: -0.1700
Data Index: 3667626 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.3525. Min Act: -0.1700
Data Index: 4038755 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.3525. Min Act: -0.1700
Data Index: 4700163 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2275. Min Range: -9.2275
Max Act: 8.3525. Min Act: -0.1700
Data Index: 5276908 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19