Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8690. Min Act: -0.1700
Data Index: 7506645 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 2812123 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.4003. Min Act: -0.1700
Data Index: 7911375 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 3383990 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.0878. Min Act: -0.1700
Data Index: 5315127 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 8625548 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9628. Min Act: -0.1700
Data Index: 5905079 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 3431058 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 4066299 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9003. Min Act: -0.1700
Data Index: 6983550 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 5066066 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 1636608 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7173232 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9003. Min Act: -0.1700
Data Index: 3462961 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8378. Min Act: -0.1700
Data Index: 5797136 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8065. Min Act: -0.1700
Data Index: 1696202 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.7753. Min Act: -0.1700
Data Index: 187829 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8065. Min Act: -0.1700
Data Index: 1349786 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.8065. Min Act: -0.1700
Data Index: 6494496 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.7753. Min Act: -0.1700
Data Index: 335013 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19