Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8703. Min Act: -0.1700
Data Index: 1441050 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8703. Min Act: -0.1700
Data Index: 1231244 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.9016. Min Act: -0.1700
Data Index: 4061692 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8391. Min Act: -0.1700
Data Index: 8108704 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8391. Min Act: -0.1700
Data Index: 2619563 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8703. Min Act: -0.1700
Data Index: 2619573 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8078. Min Act: -0.1700
Data Index: 593747 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.8078. Min Act: -0.1700
Data Index: 802763 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 7109904 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7766. Min Act: -0.1700
Data Index: 8503829 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7766. Min Act: -0.1700
Data Index: 1517333 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 8172886 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 1872186 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7141. Min Act: -0.1700
Data Index: 5591822 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 3938368 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2477904 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7453. Min Act: -0.1700
Data Index: 1231243 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6405001 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2619568 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9016. Min Range: -5.9016
Max Act: 5.6828. Min Act: -0.1700
Data Index: 1167070 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19