Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.3641. Min Act: -0.1700
Data Index: 3166479 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.3016. Min Act: -0.1700
Data Index: 3742751 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.2078. Min Act: -0.1700
Data Index: 8624429 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.1453. Min Act: -0.1700
Data Index: 3342046 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.1141. Min Act: -0.1700
Data Index: 4466766 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.1141. Min Act: -0.1700
Data Index: 7203682 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.0828. Min Act: -0.1700
Data Index: 8727962 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.0516. Min Act: -0.1700
Data Index: 7623531 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.0516. Min Act: -0.1700
Data Index: 582163 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3641. Min Range: -6.3641
Max Act: 6.0203. Min Act: -0.1700
Data Index: 3850047 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.9891. Min Act: -0.1700
Data Index: 8240959 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.9578. Min Act: -0.1700
Data Index: 1413711 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6794554 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8641. Min Act: -0.1700
Data Index: 8688001 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8641. Min Act: -0.1700
Data Index: 6751889 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5335486 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8328. Min Act: -0.1700
Data Index: 73421 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8016. Min Act: -0.1700
Data Index: 1913400 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8016. Min Act: -0.1700
Data Index: 4847043 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3641. Min Range: -6.3641
Max Act: 5.8016. Min Act: -0.1700
Data Index: 8447684 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19