Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0217. Min Range: -4.0217
Max Act: 4.0217. Min Act: -0.1700
Data Index: 1686862 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.9905. Min Act: -0.1700
Data Index: 6268515 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.9279. Min Act: -0.1700
Data Index: 1310552 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8967. Min Act: -0.1700
Data Index: 7983235 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8967. Min Act: -0.1700
Data Index: 2338320 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8967. Min Act: -0.1700
Data Index: 8055619 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8654. Min Act: -0.1700
Data Index: 5813018 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8654. Min Act: -0.1700
Data Index: 7848175 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8654. Min Act: -0.1700
Data Index: 2867522 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8654. Min Act: -0.1700
Data Index: 7265382 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8341. Min Act: -0.1700
Data Index: 7596617 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8341. Min Act: -0.1700
Data Index: 1372509 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8341. Min Act: -0.1700
Data Index: 766366 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8341. Min Act: -0.1700
Data Index: 8122376 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8029. Min Act: -0.1700
Data Index: 3254685 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8029. Min Act: -0.1700
Data Index: 6307458 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4669060 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8341. Min Act: -0.1700
Data Index: 6792801 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8029. Min Act: -0.1700
Data Index: 6598335 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0217. Min Range: -4.0217
Max Act: 3.8029. Min Act: -0.1700
Data Index: 163683 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19