Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4908 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.4246. Min Act: -0.1700
Data Index: 674008 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.4246. Min Act: -0.1700
Data Index: 6882359 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2996. Min Act: -0.1700
Data Index: 4035441 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2684. Min Act: -0.1700
Data Index: 8187049 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2684. Min Act: -0.1700
Data Index: 2591498 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2996. Min Act: -0.1700
Data Index: 5935379 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2371. Min Act: -0.1700
Data Index: 2692930 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2371. Min Act: -0.1700
Data Index: 4443296 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.2059. Min Act: -0.1700
Data Index: 5718862 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.1434. Min Act: -0.1700
Data Index: 7374246 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.1121. Min Act: -0.1700
Data Index: 2558055 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4230360 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.1121. Min Act: -0.1700
Data Index: 1216462 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0809. Min Act: -0.1700
Data Index: 7777349 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8254668 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0496. Min Act: -0.1700
Data Index: 7883137 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0184. Min Act: -0.1700
Data Index: 1308079 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0184. Min Act: -0.1700
Data Index: 2650345 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7732118 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4246. Min Range: -5.4246
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7777347 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19