Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0795. Min Act: -0.1700
Data Index: 5833464 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8920. Min Act: -0.1700
Data Index: 8282930 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.6107. Min Act: -0.1700
Data Index: 2612606 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.5482. Min Act: -0.1700
Data Index: 2309450 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.5170. Min Act: -0.1700
Data Index: 5377234 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.4857. Min Act: -0.1700
Data Index: 7065049 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.4232. Min Act: -0.1700
Data Index: 4017107 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.3920. Min Act: -0.1700
Data Index: 3978442 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.3607. Min Act: -0.1700
Data Index: 4944472 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2982. Min Act: -0.1700
Data Index: 4714462 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.3607. Min Act: -0.1700
Data Index: 670653 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2982. Min Act: -0.1700
Data Index: 8741894 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2670. Min Act: -0.1700
Data Index: 2718329 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2670. Min Act: -0.1700
Data Index: 5397090 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2357. Min Act: -0.1700
Data Index: 7809650 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2357. Min Act: -0.1700
Data Index: 8767916 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.1732. Min Act: -0.1700
Data Index: 1376015 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2357. Min Act: -0.1700
Data Index: 7502323 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2045. Min Act: -0.1700
Data Index: 1969400 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.2045. Min Act: -0.1700
Data Index: 825675 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19