Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4800 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.5640. Min Act: -0.1700
Data Index: 3468711 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.5015. Min Act: -0.1700
Data Index: 1940078 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.4702. Min Act: -0.1700
Data Index: 2283471 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3765. Min Act: -0.1700
Data Index: 6675755 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.4077. Min Act: -0.1700
Data Index: 1916572 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3765. Min Act: -0.1700
Data Index: 714477 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3765. Min Act: -0.1700
Data Index: 6111593 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3452. Min Act: -0.1700
Data Index: 1639162 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3140. Min Act: -0.1700
Data Index: 3412591 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3452. Min Act: -0.1700
Data Index: 7612336 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3452. Min Act: -0.1700
Data Index: 7851628 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3140. Min Act: -0.1700
Data Index: 6185971 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3140. Min Act: -0.1700
Data Index: 7497518 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3452. Min Act: -0.1700
Data Index: 2945046 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3140. Min Act: -0.1700
Data Index: 423612 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.3140. Min Act: -0.1700
Data Index: 519743 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.2827. Min Act: -0.1700
Data Index: 5499153 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.2827. Min Act: -0.1700
Data Index: 2790152 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.2827. Min Act: -0.1700
Data Index: 8697332 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5640. Min Range: -4.5640
Max Act: 4.2827. Min Act: -0.1700
Data Index: 7605654 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19