Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5941 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4613856 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4134212 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.9176. Min Act: -0.1700
Data Index: 2466155 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.7926. Min Act: -0.1700
Data Index: 8544829 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.7301. Min Act: -0.1700
Data Index: 1805357 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6676. Min Act: -0.1700
Data Index: 7959337 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6988. Min Act: -0.1700
Data Index: 718106 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6988. Min Act: -0.1700
Data Index: 1913564 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6676. Min Act: -0.1700
Data Index: 4187779 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6363. Min Act: -0.1700
Data Index: 1930948 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6363. Min Act: -0.1700
Data Index: 2582288 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6051. Min Act: -0.1700
Data Index: 2220059 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6363. Min Act: -0.1700
Data Index: 2466153 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.6051. Min Act: -0.1700
Data Index: 7038075 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 8170256 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 3696331 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 8448675 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 1392123 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 6176087 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9488. Min Range: -5.9488
Max Act: 5.5738. Min Act: -0.1700
Data Index: 3643790 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19