Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5328 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.8670. Min Act: -0.1700
Data Index: 4749032 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3154885 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.7732. Min Act: -0.1700
Data Index: 2421598 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.7420. Min Act: -0.1700
Data Index: 2389910 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.7420. Min Act: -0.1700
Data Index: 4870592 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.7107. Min Act: -0.1700
Data Index: 4721165 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6795. Min Act: -0.1700
Data Index: 8756662 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6795. Min Act: -0.1700
Data Index: 1744589 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6795. Min Act: -0.1700
Data Index: 7093543 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 7089854 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6795. Min Act: -0.1700
Data Index: 5733179 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 3412543 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 5750933 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 3656523 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6170. Min Act: -0.1700
Data Index: 3126713 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6170. Min Act: -0.1700
Data Index: 3554319 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6170. Min Act: -0.1700
Data Index: 3626752 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.5857. Min Act: -0.1700
Data Index: 991245 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 2661985 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8670. Min Range: -4.8670
Max Act: 4.6482. Min Act: -0.1700
Data Index: 8481883 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19