Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3573. Min Range: -4.3573
Max Act: 4.3573. Min Act: -0.1700
Data Index: 2478706 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3573. Min Range: -4.3573
Max Act: 4.0448. Min Act: -0.1700
Data Index: 5591100 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.9197. Min Act: -0.1700
Data Index: 8568107 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8885. Min Act: -0.1700
Data Index: 1307609 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8885. Min Act: -0.1700
Data Index: 3569620 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8885. Min Act: -0.1700
Data Index: 4952240 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8885. Min Act: -0.1700
Data Index: 5281161 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8572. Min Act: -0.1700
Data Index: 820438 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8572. Min Act: -0.1700
Data Index: 8364101 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8572. Min Act: -0.1700
Data Index: 564764 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8259. Min Act: -0.1700
Data Index: 1969806 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8259. Min Act: -0.1700
Data Index: 708109 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.8259. Min Act: -0.1700
Data Index: 5181107 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7947. Min Act: -0.1700
Data Index: 3989830 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5550856 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7790. Min Act: -0.1700
Data Index: 2068087 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7634. Min Act: -0.1700
Data Index: 2012165 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7634. Min Act: -0.1700
Data Index: 2304607 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7790. Min Act: -0.1700
Data Index: 2929319 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3573. Min Range: -4.3573
Max Act: 3.7634. Min Act: -0.1700
Data Index: 7245847 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19