Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4718. Min Range: -6.4718
Max Act: 6.4718. Min Act: -0.1700
Data Index: 7104880 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4718. Min Range: -6.4718
Max Act: 6.3468. Min Act: -0.1700
Data Index: 1759355 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4718. Min Range: -6.4718
Max Act: 6.1905. Min Act: -0.1700
Data Index: 4282573 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.8155. Min Act: -0.1700
Data Index: 647679 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6905. Min Act: -0.1700
Data Index: 7577414 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.7843. Min Act: -0.1700
Data Index: 5916427 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6905. Min Act: -0.1700
Data Index: 3204772 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6593. Min Act: -0.1700
Data Index: 6128439 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6593. Min Act: -0.1700
Data Index: 1995149 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6280. Min Act: -0.1700
Data Index: 3099029 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5343. Min Act: -0.1700
Data Index: 1290690 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.6280. Min Act: -0.1700
Data Index: 7987152 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5655. Min Act: -0.1700
Data Index: 5731700 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5655. Min Act: -0.1700
Data Index: 7847286 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5655. Min Act: -0.1700
Data Index: 1096108 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5030. Min Act: -0.1700
Data Index: 2210241 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5655. Min Act: -0.1700
Data Index: 7099528 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5343. Min Act: -0.1700
Data Index: 4517854 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5030. Min Act: -0.1700
Data Index: 7695809 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4718. Min Range: -6.4718
Max Act: 5.5030. Min Act: -0.1700
Data Index: 1683274 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19