Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.9913. Min Act: -0.1700
Data Index: 397156 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.9288. Min Act: -0.1700
Data Index: 5831434 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8975. Min Act: -0.1700
Data Index: 885960 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8975. Min Act: -0.1700
Data Index: 3155122 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8663. Min Act: -0.1700
Data Index: 2763245 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8663. Min Act: -0.1700
Data Index: 421655 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8350. Min Act: -0.1700
Data Index: 164837 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8350. Min Act: -0.1700
Data Index: 6332726 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8350. Min Act: -0.1700
Data Index: 4467765 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8350. Min Act: -0.1700
Data Index: 3577385 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 3577384 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8037. Min Act: -0.1700
Data Index: 5666758 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 7822401 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8037. Min Act: -0.1700
Data Index: 3952064 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 890894 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 4889457 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 7068985 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 6586772 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7725. Min Act: -0.1700
Data Index: 5838259 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.8037. Min Act: -0.1700
Data Index: 2916929 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19