Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.3834. Min Act: -0.1700
Data Index: 105207 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.2584. Min Act: -0.1700
Data Index: 7838054 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.1959. Min Act: -0.1700
Data Index: 718369 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.1646. Min Act: -0.1700
Data Index: 3540944 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.1021. Min Act: -0.1700
Data Index: 5202961 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0708. Min Act: -0.1700
Data Index: 2102561 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0708. Min Act: -0.1700
Data Index: 1345782 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0708. Min Act: -0.1700
Data Index: 6342178 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0083. Min Act: -0.1700
Data Index: 4944675 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0396. Min Act: -0.1700
Data Index: 1467157 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0083. Min Act: -0.1700
Data Index: 1955851 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0083. Min Act: -0.1700
Data Index: 6797487 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3834. Min Range: -4.3834
Max Act: 4.0083. Min Act: -0.1700
Data Index: 8764460 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9771. Min Act: -0.1700
Data Index: 8556577 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9458. Min Act: -0.1700
Data Index: 6161624 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9771. Min Act: -0.1700
Data Index: 8730565 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9458. Min Act: -0.1700
Data Index: 4530360 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9458. Min Act: -0.1700
Data Index: 8446880 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9145. Min Act: -0.1700
Data Index: 1262882 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3834. Min Range: -4.3834
Max Act: 3.9458. Min Act: -0.1700
Data Index: 5012090 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19