Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5609 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1051. Min Range: -4.1051
Max Act: 4.1051. Min Act: -0.1700
Data Index: 279822 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.9801. Min Act: -0.1700
Data Index: 7364009 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.8081. Min Act: -0.1700
Data Index: 184713 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.8394. Min Act: -0.1700
Data Index: 279816 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.7455. Min Act: -0.1700
Data Index: 7555462 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.7299. Min Act: -0.1700
Data Index: 6147989 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.7143. Min Act: -0.1700
Data Index: 140714 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6517. Min Act: -0.1700
Data Index: 6633072 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6673. Min Act: -0.1700
Data Index: 1038284 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6517. Min Act: -0.1700
Data Index: 4537613 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6204. Min Act: -0.1700
Data Index: 8085776 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6360. Min Act: -0.1700
Data Index: 279823 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5891. Min Act: -0.1700
Data Index: 7728470 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.6047. Min Act: -0.1700
Data Index: 2003013 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5734. Min Act: -0.1700
Data Index: 8628177 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5734. Min Act: -0.1700
Data Index: 2896677 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5578. Min Act: -0.1700
Data Index: 6827231 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5734. Min Act: -0.1700
Data Index: 279812 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5578. Min Act: -0.1700
Data Index: 5614333 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1051. Min Range: -4.1051
Max Act: 3.5265. Min Act: -0.1700
Data Index: 6384703 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19