Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1067. Min Range: -5.1067
Max Act: 5.1067. Min Act: -0.1700
Data Index: 4101292 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1067. Min Range: -5.1067
Max Act: 5.0442. Min Act: -0.1700
Data Index: 4668073 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9504. Min Act: -0.1700
Data Index: 991559 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9504. Min Act: -0.1700
Data Index: 3046413 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5766338 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4854907 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5021267 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3439969 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9192. Min Act: -0.1700
Data Index: 7610178 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.9192. Min Act: -0.1700
Data Index: 6349327 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 308868 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 7284669 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 930890 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 979139 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 4233292 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3744112 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 5602716 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 2160966 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.8567. Min Act: -0.1700
Data Index: 8118247 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1067. Min Range: -5.1067
Max Act: 4.7942. Min Act: -0.1700
Data Index: 4144344 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19