Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0482. Min Range: -8.0482
Max Act: 8.0482. Min Act: -0.1700
Data Index: 6314425 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.9232. Min Act: -0.1700
Data Index: 6314426 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 4747473 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 8530715 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 3849027 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 157918 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.7982. Min Act: -0.1700
Data Index: 3849028 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.6419. Min Act: -0.1700
Data Index: 3269437 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.6419. Min Act: -0.1700
Data Index: 3412249 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.6107. Min Act: -0.1700
Data Index: 2052245 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.6107. Min Act: -0.1700
Data Index: 5650500 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.5794. Min Act: -0.1700
Data Index: 6260052 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.5794. Min Act: -0.1700
Data Index: 4747472 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.5482. Min Act: -0.1700
Data Index: 3397845 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7986516 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.5169. Min Act: -0.1700
Data Index: 8530714 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.4857. Min Act: -0.1700
Data Index: 6871516 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7986515 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.4232. Min Act: -0.1700
Data Index: 3269436 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0482. Min Range: -8.0482
Max Act: 7.4232. Min Act: -0.1700
Data Index: 5650501 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19