Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.7039. Min Act: -0.1700
Data Index: 5741283 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.5164. Min Act: -0.1700
Data Index: 7607750 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.4852. Min Act: -0.1700
Data Index: 6660562 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.4227. Min Act: -0.1700
Data Index: 7607757 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.4227. Min Act: -0.1700
Data Index: 575521 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.3602. Min Act: -0.1700
Data Index: 5607095 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.3602. Min Act: -0.1700
Data Index: 227364 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.3602. Min Act: -0.1700
Data Index: 4195481 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2039. Min Act: -0.1700
Data Index: 3527834 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2352. Min Act: -0.1700
Data Index: 2885461 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2039. Min Act: -0.1700
Data Index: 455141 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2352. Min Act: -0.1700
Data Index: 2627525 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2352. Min Act: -0.1700
Data Index: 7296754 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.2039. Min Act: -0.1700
Data Index: 2342143 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1727. Min Act: -0.1700
Data Index: 8315435 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1414. Min Act: -0.1700
Data Index: 8558247 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1727. Min Act: -0.1700
Data Index: 3061472 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6733227 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1102. Min Act: -0.1700
Data Index: 2266965 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7039. Min Range: -6.7039
Max Act: 6.1102. Min Act: -0.1700
Data Index: 4421033 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19