Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.8478. Min Act: -0.1700
Data Index: 2084366 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1744630 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.5665. Min Act: -0.1700
Data Index: 2333523 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.5353. Min Act: -0.1700
Data Index: 1929721 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.4728. Min Act: -0.1700
Data Index: 1675721 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.4103. Min Act: -0.1700
Data Index: 3622717 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7083961 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.3478. Min Act: -0.1700
Data Index: 7444970 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2540. Min Act: -0.1700
Data Index: 503181 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2540. Min Act: -0.1700
Data Index: 8811796 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2228. Min Act: -0.1700
Data Index: 168536 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2228. Min Act: -0.1700
Data Index: 4150866 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2228. Min Act: -0.1700
Data Index: 6846762 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.2228. Min Act: -0.1700
Data Index: 4822048 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1915. Min Act: -0.1700
Data Index: 335970 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1915. Min Act: -0.1700
Data Index: 4911036 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1915. Min Act: -0.1700
Data Index: 8702883 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1915. Min Act: -0.1700
Data Index: 5272510 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1603. Min Act: -0.1700
Data Index: 8702886 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8478. Min Range: -6.8478
Max Act: 6.1603. Min Act: -0.1700
Data Index: 4639004 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19