Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.7655. Min Act: -0.1700
Data Index: 5578854 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6608213 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.6718. Min Act: -0.1700
Data Index: 1275036 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.7030. Min Act: -0.1700
Data Index: 3468477 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 6535820 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.6405. Min Act: -0.1700
Data Index: 413441 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.6093. Min Act: -0.1700
Data Index: 1911074 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.6093. Min Act: -0.1700
Data Index: 2856334 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5780. Min Act: -0.1700
Data Index: 6264798 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5780. Min Act: -0.1700
Data Index: 551040 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 8823677 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5780. Min Act: -0.1700
Data Index: 6440876 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 5803639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 370344 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 5995568 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 6777902 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 3833788 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.4843. Min Act: -0.1700
Data Index: 4526524 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5468. Min Act: -0.1700
Data Index: 7835703 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7655. Min Range: -5.7655
Max Act: 5.5155. Min Act: -0.1700
Data Index: 7985332 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19