Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4721. Min Range: -11.4721
Max Act: 11.4721. Min Act: -0.1700
Data Index: 230648 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4721. Min Range: -11.4721
Max Act: 11.3471. Min Act: -0.1700
Data Index: 4023697 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4721. Min Range: -11.4721
Max Act: 11.1596. Min Act: -0.1700
Data Index: 3462624 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.9721. Min Act: -0.1700
Data Index: 1215049 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.9721. Min Act: -0.1700
Data Index: 1505086 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.9096. Min Act: -0.1700
Data Index: 3182179 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.8471. Min Act: -0.1700
Data Index: 7896310 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.8471. Min Act: -0.1700
Data Index: 8042686 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.7846. Min Act: -0.1700
Data Index: 6731423 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.7846. Min Act: -0.1700
Data Index: 4257944 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.7221. Min Act: -0.1700
Data Index: 6618010 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.7846. Min Act: -0.1700
Data Index: 2438007 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.6596. Min Act: -0.1700
Data Index: 3990571 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.6596. Min Act: -0.1700
Data Index: 2040971 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.6596. Min Act: -0.1700
Data Index: 85292 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.5971. Min Act: -0.1700
Data Index: 1900237 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.5971. Min Act: -0.1700
Data Index: 2210522 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.5971. Min Act: -0.1700
Data Index: 3512185 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.5971. Min Act: -0.1700
Data Index: 140990 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4721. Min Range: -11.4721
Max Act: 10.5346. Min Act: -0.1700
Data Index: 5271230 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19