Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7433. Min Range: -12.7433
Max Act: 12.7433. Min Act: -0.1700
Data Index: 8587570 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7433. Min Range: -12.7433
Max Act: 12.4308. Min Act: -0.1700
Data Index: 3652407 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7433. Min Range: -12.7433
Max Act: 12.2433. Min Act: -0.1700
Data Index: 2071093 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7433. Min Range: -12.7433
Max Act: 12.0558. Min Act: -0.1700
Data Index: 6664982 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.9308. Min Act: -0.1700
Data Index: 2829419 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.9308. Min Act: -0.1700
Data Index: 216692 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8683. Min Act: -0.1700
Data Index: 2112516 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8058. Min Act: -0.1700
Data Index: 5750643 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8683. Min Act: -0.1700
Data Index: 7173500 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8683. Min Act: -0.1700
Data Index: 3557020 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8683. Min Act: -0.1700
Data Index: 5511391 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8683. Min Act: -0.1700
Data Index: 7049324 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8058. Min Act: -0.1700
Data Index: 8430701 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8058. Min Act: -0.1700
Data Index: 2849884 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8058. Min Act: -0.1700
Data Index: 522805 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.8058. Min Act: -0.1700
Data Index: 6604328 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.7433. Min Act: -0.1700
Data Index: 4209609 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.7433. Min Act: -0.1700
Data Index: 4193410 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.6808. Min Act: -0.1700
Data Index: 3873505 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7433. Min Range: -12.7433
Max Act: 11.7433. Min Act: -0.1700
Data Index: 2002286 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19