Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8868. Min Act: -0.1700
Data Index: 1827116 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7930. Min Act: -0.1700
Data Index: 2936514 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7930. Min Act: -0.1700
Data Index: 4842605 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7618. Min Act: -0.1696
Data Index: 3618964 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7930. Min Act: -0.1700
Data Index: 8026131 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7305. Min Act: -0.1700
Data Index: 7851723 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6368. Min Act: -0.1700
Data Index: 4337325 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6055. Min Act: -0.1700
Data Index: 2802635 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5743. Min Act: -0.1700
Data Index: 4867680 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5430. Min Act: -0.1700
Data Index: 4188008 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5430. Min Act: -0.1700
Data Index: 1358049 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5118. Min Act: -0.1700
Data Index: 3490711 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5118. Min Act: -0.1700
Data Index: 4501574 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4805. Min Act: -0.1700
Data Index: 4609426 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4805. Min Act: -0.1700
Data Index: 5664446 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4805. Min Act: -0.1700
Data Index: 1824221 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4493. Min Act: -0.1700
Data Index: 2728407 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4493. Min Act: -0.1700
Data Index: 4191943 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4493. Min Act: -0.1700
Data Index: 2540491 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.4493. Min Act: -0.1700
Data Index: 321910 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19