Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6355 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.4180. Min Act: -0.1700
Data Index: 7838580 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.4180. Min Act: -0.1700
Data Index: 7638901 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.3243. Min Act: -0.1700
Data Index: 4192108 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.3243. Min Act: -0.1700
Data Index: 656584 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.2305. Min Act: -0.1700
Data Index: 7027616 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.1993. Min Act: -0.1700
Data Index: 5124413 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.1993. Min Act: -0.1700
Data Index: 6274726 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.1368. Min Act: -0.1700
Data Index: 259812 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.0743. Min Act: -0.1700
Data Index: 4362892 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.0118. Min Act: -0.1700
Data Index: 2421507 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.0430. Min Act: -0.1700
Data Index: 4847818 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4180. Min Range: -8.4180
Max Act: 8.0430. Min Act: -0.1700
Data Index: 3245832 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.9493. Min Act: -0.1700
Data Index: 6995211 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.9493. Min Act: -0.1700
Data Index: 2858583 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.9180. Min Act: -0.1700
Data Index: 8596622 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.9180. Min Act: -0.1700
Data Index: 265547 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.8555. Min Act: -0.1700
Data Index: 3758309 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.8555. Min Act: -0.1700
Data Index: 736310 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.8243. Min Act: -0.1700
Data Index: 6080577 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4180. Min Range: -8.4180
Max Act: 7.8555. Min Act: -0.1700
Data Index: 2190769 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19