Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.3504. Min Act: -0.1700
Data Index: 2635491 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.3192. Min Act: -0.1700
Data Index: 1591850 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.2879. Min Act: -0.1700
Data Index: 5030042 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.2567. Min Act: -0.1700
Data Index: 4791952 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.2254. Min Act: -0.1700
Data Index: 3371788 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1942. Min Act: -0.1700
Data Index: 8013857 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 3343140 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 8094733 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 2365480 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 2685737 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 1675559 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1004. Min Act: -0.1700
Data Index: 3303857 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1317. Min Act: -0.1700
Data Index: 3105949 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1317. Min Act: -0.1700
Data Index: 6393637 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1004. Min Act: -0.1700
Data Index: 2720459 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.1004. Min Act: -0.1700
Data Index: 7709809 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3957936 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.0067. Min Act: -0.1700
Data Index: 8601783 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3504. Min Range: -5.3504
Max Act: 5.0379. Min Act: -0.1700
Data Index: 6905023 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3504. Min Range: -5.3504
Max Act: 4.9754. Min Act: -0.1700
Data Index: 1393505 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19