Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5648 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8232. Min Range: -6.8232
Max Act: 6.8232. Min Act: -0.1700
Data Index: 6291955 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8232. Min Range: -6.8232
Max Act: 6.1357. Min Act: -0.1700
Data Index: 8110242 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8232. Min Range: -6.8232
Max Act: 6.1357. Min Act: -0.1700
Data Index: 6941741 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8232. Min Range: -6.8232
Max Act: 6.0107. Min Act: -0.1700
Data Index: 7361143 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.9482. Min Act: -0.1700
Data Index: 3772647 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7920. Min Act: -0.1700
Data Index: 322380 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7607. Min Act: -0.1700
Data Index: 8785043 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7607. Min Act: -0.1700
Data Index: 2078679 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7607. Min Act: -0.1700
Data Index: 1541796 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7295. Min Act: -0.1700
Data Index: 7084563 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.7295. Min Act: -0.1700
Data Index: 571110 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6982. Min Act: -0.1700
Data Index: 7623017 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6670. Min Act: -0.1700
Data Index: 4878199 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 2849066 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6357. Min Act: -0.1700
Data Index: 6938281 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 5232675 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8000788 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 494781 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8353530 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8232. Min Range: -6.8232
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5026042 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19