Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5902 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.7106. Min Act: -0.1700
Data Index: 6061538 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.6481. Min Act: -0.1700
Data Index: 8416745 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5544. Min Act: -0.1700
Data Index: 6550885 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5856. Min Act: -0.1700
Data Index: 7406920 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5856. Min Act: -0.1700
Data Index: 4867408 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5856. Min Act: -0.1700
Data Index: 316917 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5135600 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5231. Min Act: -0.1700
Data Index: 1324706 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5231. Min Act: -0.1700
Data Index: 872800 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4919. Min Act: -0.1700
Data Index: 7009917 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.5231. Min Act: -0.1700
Data Index: 8252080 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4919. Min Act: -0.1700
Data Index: 3789404 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4919. Min Act: -0.1700
Data Index: 2863321 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4919. Min Act: -0.1700
Data Index: 5389391 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4294. Min Act: -0.1700
Data Index: 6150847 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4606. Min Act: -0.1700
Data Index: 4737483 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4606. Min Act: -0.1700
Data Index: 3737668 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4294. Min Act: -0.1700
Data Index: 246767 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.4294. Min Act: -0.1700
Data Index: 199317 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7106. Min Range: -4.7106
Max Act: 4.3981. Min Act: -0.1700
Data Index: 932243 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19