Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0428. Min Range: -3.0428
Max Act: 3.0428. Min Act: -0.1700
Data Index: 5658409 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.9321. Min Act: -0.1700
Data Index: 7077058 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8687. Min Act: -0.1700
Data Index: 8678890 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8528. Min Act: -0.1700
Data Index: 581924 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8369. Min Act: -0.1700
Data Index: 604815 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8210. Min Act: -0.1700
Data Index: 1680931 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8051. Min Act: -0.1700
Data Index: 1399989 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.8051. Min Act: -0.1700
Data Index: 5239579 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7732. Min Act: -0.1700
Data Index: 6478321 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7892. Min Act: -0.1700
Data Index: 3782459 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7732. Min Act: -0.1700
Data Index: 2535344 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7732. Min Act: -0.1700
Data Index: 7800987 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7732. Min Act: -0.1700
Data Index: 3752232 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 6863635 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 8122868 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 8437457 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 5720377 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 6176015 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7573. Min Act: -0.1700
Data Index: 7585196 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0428. Min Range: -3.0428
Max Act: 2.7732. Min Act: -0.1700
Data Index: 7570071 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19