Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.8790. Min Act: -0.1700
Data Index: 7511287 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.5978. Min Act: -0.1700
Data Index: 43948 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.5040. Min Act: -0.1700
Data Index: 1390489 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.3790. Min Act: -0.1700
Data Index: 6105313 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.4103. Min Act: -0.1700
Data Index: 3813567 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.3790. Min Act: -0.1700
Data Index: 5483195 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.3478. Min Act: -0.1700
Data Index: 6848219 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.3478. Min Act: -0.1700
Data Index: 4710902 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.2853. Min Act: -0.1700
Data Index: 2333653 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.2540. Min Act: -0.1700
Data Index: 8392168 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.2540. Min Act: -0.1700
Data Index: 7339845 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.2228. Min Act: -0.1700
Data Index: 331864 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 2615773 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 2534685 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 5990442 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 1801810 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 3802405 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1603. Min Act: -0.1700
Data Index: 7586657 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1603. Min Act: -0.1700
Data Index: 1431315 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8790. Min Range: -4.8790
Max Act: 4.1915. Min Act: -0.1700
Data Index: 151694 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19