Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.3828. Min Act: -0.1700
Data Index: 6346019 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.4141. Min Act: -0.1700
Data Index: 374576 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.4453. Min Act: -0.1700
Data Index: 3761800 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.4141. Min Act: -0.1700
Data Index: 6162633 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.3516. Min Act: -0.1700
Data Index: 553533 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.3516. Min Act: -0.1700
Data Index: 4125902 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.3516. Min Act: -0.1700
Data Index: 4670533 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.3516. Min Act: -0.1700
Data Index: 4350710 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2891. Min Act: -0.1700
Data Index: 7727575 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2891. Min Act: -0.1700
Data Index: 6737053 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2891. Min Act: -0.1700
Data Index: 1239530 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2891. Min Act: -0.1700
Data Index: 5855342 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2578. Min Act: -0.1700
Data Index: 5882794 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2578. Min Act: -0.1700
Data Index: 17095 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2265. Min Act: -0.1700
Data Index: 6737055 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.2578. Min Act: -0.1700
Data Index: 5210409 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.1953. Min Act: -0.1700
Data Index: 286711 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.1953. Min Act: -0.1700
Data Index: 5794161 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.1640. Min Act: -0.1700
Data Index: 6884927 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4453. Min Range: -4.4453
Max Act: 4.1953. Min Act: -0.1700
Data Index: 732467 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19