Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.2412. Min Act: -0.1700
Data Index: 3558326 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.1787. Min Act: -0.1700
Data Index: 4207416 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.0850. Min Act: -0.1700
Data Index: 5077760 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.0225. Min Act: -0.1700
Data Index: 7947835 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9912. Min Act: -0.1700
Data Index: 5830326 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2412. Min Range: -7.2412
Max Act: 7.0225. Min Act: -0.1700
Data Index: 285226 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9912. Min Act: -0.1700
Data Index: 6923370 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9600. Min Act: -0.1700
Data Index: 2994514 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6373162 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.9287. Min Act: -0.1700
Data Index: 3330962 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8662. Min Act: -0.1700
Data Index: 3360849 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8662. Min Act: -0.1700
Data Index: 722222 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 3168676 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7432971 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 1102851 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.8037. Min Act: -0.1700
Data Index: 3763883 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7725. Min Act: -0.1700
Data Index: 8401329 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7100. Min Act: -0.1700
Data Index: 6705633 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.7100. Min Act: -0.1700
Data Index: 6542555 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2412. Min Range: -7.2412
Max Act: 6.6787. Min Act: -0.1700
Data Index: 5389173 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19