Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1407 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0025. Min Range: -6.0025
Max Act: 6.0025. Min Act: -0.1700
Data Index: 2315093 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.9088. Min Act: -0.1700
Data Index: 7453837 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.8775. Min Act: -0.1700
Data Index: 79623 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.8150. Min Act: -0.1700
Data Index: 3224751 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.8150. Min Act: -0.1700
Data Index: 6757330 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7838. Min Act: -0.1700
Data Index: 3790783 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2620944 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7525. Min Act: -0.1700
Data Index: 1183997 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7525. Min Act: -0.1700
Data Index: 6141517 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7525. Min Act: -0.1700
Data Index: 7950201 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7213. Min Act: -0.1700
Data Index: 5638253 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7525. Min Act: -0.1700
Data Index: 582847 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7213. Min Act: -0.1700
Data Index: 3982436 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7213. Min Act: -0.1700
Data Index: 6141516 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.6900. Min Act: -0.1700
Data Index: 7527638 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7213. Min Act: -0.1700
Data Index: 4171699 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.6588. Min Act: -0.1700
Data Index: 1749925 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.6900. Min Act: -0.1700
Data Index: 1019592 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.7213. Min Act: -0.1700
Data Index: 6850583 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0025. Min Range: -6.0025
Max Act: 5.6900. Min Act: -0.1700
Data Index: 193539 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19