Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2219 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.6923. Min Act: -0.1700
Data Index: 3247929 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.6923. Min Act: -0.1700
Data Index: 2215741 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.6611. Min Act: -0.1700
Data Index: 1421909 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.6298. Min Act: -0.1700
Data Index: 4578362 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.5986. Min Act: -0.1700
Data Index: 1749887 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.5361. Min Act: -0.1700
Data Index: 1177340 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.5673. Min Act: -0.1700
Data Index: 7889535 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.5361. Min Act: -0.1700
Data Index: 2268068 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.4736. Min Act: -0.1700
Data Index: 4045491 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.4423. Min Act: -0.1700
Data Index: 1014517 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.4423. Min Act: -0.1700
Data Index: 8111076 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.4111. Min Act: -0.1700
Data Index: 2863547 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3798. Min Act: -0.1700
Data Index: 4824148 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3798. Min Act: -0.1700
Data Index: 3411050 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3486. Min Act: -0.1700
Data Index: 6153124 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3486. Min Act: -0.1700
Data Index: 6686549 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3173. Min Act: -0.1700
Data Index: 1011149 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3173. Min Act: -0.1700
Data Index: 7570575 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3173. Min Act: -0.1700
Data Index: 7797498 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6923. Min Range: -5.6923
Max Act: 5.3173. Min Act: -0.1700
Data Index: 5722895 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19