Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.5440. Min Act: -0.1700
Data Index: 5950278 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.4815. Min Act: -0.1700
Data Index: 2112255 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.4190. Min Act: -0.1700
Data Index: 959904 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.3565. Min Act: -0.1700
Data Index: 3989204 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.3877. Min Act: -0.1700
Data Index: 7692880 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.3565. Min Act: -0.1700
Data Index: 7192381 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.2940. Min Act: -0.1700
Data Index: 6541704 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.2315. Min Act: -0.1700
Data Index: 3989201 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.2002. Min Act: -0.1700
Data Index: 3758414 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1690. Min Act: -0.1700
Data Index: 1183942 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1690. Min Act: -0.1700
Data Index: 5550915 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1690. Min Act: -0.1700
Data Index: 6297471 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 6580430 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 7911759 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 3272918 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 5989846 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 6719528 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 2066396 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1377. Min Act: -0.1700
Data Index: 4340108 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5440. Min Range: -6.5440
Max Act: 6.1065. Min Act: -0.1700
Data Index: 7312567 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19