Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2892. Min Range: -4.2892
Max Act: 4.2892. Min Act: -0.1700
Data Index: 481422 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2892. Min Range: -4.2892
Max Act: 4.1017. Min Act: -0.1700
Data Index: 6132640 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2892. Min Range: -4.2892
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1798422 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2892. Min Range: -4.2892
Max Act: 4.0392. Min Act: -0.1700
Data Index: 7038688 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2892. Min Range: -4.2892
Max Act: 4.0079. Min Act: -0.1700
Data Index: 7136513 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.9767. Min Act: -0.1700
Data Index: 458416 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.9141. Min Act: -0.1700
Data Index: 8066303 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.9141. Min Act: -0.1700
Data Index: 3148886 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.9141. Min Act: -0.1700
Data Index: 6959727 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.9454. Min Act: -0.1700
Data Index: 622409 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8516. Min Act: -0.1700
Data Index: 7502434 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8516. Min Act: -0.1700
Data Index: 3965829 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8829. Min Act: -0.1700
Data Index: 5441286 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8829. Min Act: -0.1700
Data Index: 6999861 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8203. Min Act: -0.1700
Data Index: 5607136 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8516. Min Act: -0.1700
Data Index: 6386118 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.7891. Min Act: -0.1700
Data Index: 6501701 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8516. Min Act: -0.1700
Data Index: 6585036 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8203. Min Act: -0.1700
Data Index: 4173455 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2892. Min Range: -4.2892
Max Act: 3.8203. Min Act: -0.1700
Data Index: 4628738 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19