Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1096. Min Range: -5.1096
Max Act: 5.1096. Min Act: -0.1700
Data Index: 4040369 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1096. Min Range: -5.1096
Max Act: 5.0158. Min Act: -0.1700
Data Index: 8796460 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.9846. Min Act: -0.1700
Data Index: 2498253 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.9533. Min Act: -0.1700
Data Index: 1536726 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8908. Min Act: -0.1700
Data Index: 932874 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.9533. Min Act: -0.1700
Data Index: 7910530 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8908. Min Act: -0.1700
Data Index: 7590401 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8908. Min Act: -0.1700
Data Index: 2737709 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8908. Min Act: -0.1700
Data Index: 5352066 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8596. Min Act: -0.1700
Data Index: 5178715 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8596. Min Act: -0.1700
Data Index: 3396273 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8596. Min Act: -0.1700
Data Index: 3611509 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8283. Min Act: -0.1700
Data Index: 929432 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8596. Min Act: -0.1700
Data Index: 4283172 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8596. Min Act: -0.1700
Data Index: 4953903 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.7971. Min Act: -0.1700
Data Index: 1336838 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8283. Min Act: -0.1700
Data Index: 4039393 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8283. Min Act: -0.1700
Data Index: 1378699 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8283. Min Act: -0.1700
Data Index: 4398921 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1096. Min Range: -5.1096
Max Act: 4.8283. Min Act: -0.1700
Data Index: 4730200 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19