Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.4555. Min Act: -0.1700
Data Index: 393308 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2367. Min Act: -0.1700
Data Index: 5966302 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2367. Min Act: -0.1700
Data Index: 1542120 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2367. Min Act: -0.1700
Data Index: 121868 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2055. Min Act: -0.1700
Data Index: 8125616 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2055. Min Act: -0.1700
Data Index: 5898921 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3273356 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1742. Min Act: -0.1700
Data Index: 2863545 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1742. Min Act: -0.1700
Data Index: 6393865 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2055. Min Act: -0.1700
Data Index: 8210362 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1742. Min Act: -0.1700
Data Index: 2992701 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1742. Min Act: -0.1700
Data Index: 7528182 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3769439 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1430. Min Act: -0.1700
Data Index: 2170492 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1430. Min Act: -0.1700
Data Index: 408848 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1117. Min Act: -0.1700
Data Index: 3982712 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1117. Min Act: -0.1700
Data Index: 4739885 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1430. Min Act: -0.1700
Data Index: 5259802 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1117. Min Act: -0.1700
Data Index: 6341778 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4555. Min Range: -5.4555
Max Act: 5.1117. Min Act: -0.1700
Data Index: 20836 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19