Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.4384. Min Act: -0.1700
Data Index: 936549 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.4058. Min Act: -0.1700
Data Index: 2100446 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3894. Min Act: -0.1700
Data Index: 7636204 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3731. Min Act: -0.1700
Data Index: 1390888 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3731. Min Act: -0.1700
Data Index: 6468925 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3731. Min Act: -0.1700
Data Index: 6899302 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3567. Min Act: -0.1700
Data Index: 4607914 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3404. Min Act: -0.1700
Data Index: 3511975 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3567. Min Act: -0.1700
Data Index: 2748645 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3404. Min Act: -0.1700
Data Index: 4410908 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3404. Min Act: -0.1700
Data Index: 6120205 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3239. Min Act: -0.1700
Data Index: 6840703 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3075. Min Act: -0.1700
Data Index: 6205443 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3075. Min Act: -0.1700
Data Index: 8430853 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3239. Min Act: -0.1700
Data Index: 2420493 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3239. Min Act: -0.1700
Data Index: 5789975 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3075. Min Act: -0.1700
Data Index: 1762684 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3239. Min Act: -0.1700
Data Index: 5375090 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3075. Min Act: -0.1700
Data Index: 2568850 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4384. Min Range: -2.4384
Max Act: 2.3075. Min Act: -0.1700
Data Index: 4840195 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19