Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5841 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1634. Min Range: -8.1634
Max Act: 8.1634. Min Act: -0.1700
Data Index: 6090231 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4114771 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.2571. Min Act: -0.1700
Data Index: 5540138 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.2571. Min Act: -0.1700
Data Index: 2970590 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1634. Min Act: -0.1700
Data Index: 6826737 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1634. Min Act: -0.1700
Data Index: 8219073 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1321. Min Act: -0.1700
Data Index: 1707711 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1321. Min Act: -0.1700
Data Index: 3674427 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1321. Min Act: -0.1700
Data Index: 5028933 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1009. Min Act: -0.1700
Data Index: 8396283 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1009. Min Act: -0.1700
Data Index: 4875266 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1009. Min Act: -0.1700
Data Index: 330342 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.1009. Min Act: -0.1700
Data Index: 6910823 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0696. Min Act: -0.1700
Data Index: 1886718 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0384. Min Act: -0.1700
Data Index: 4453185 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0696. Min Act: -0.1700
Data Index: 2927239 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0696. Min Act: -0.1700
Data Index: 5276847 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0071. Min Act: -0.1700
Data Index: 2421005 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0384. Min Act: -0.1700
Data Index: 493851 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1634. Min Range: -8.1634
Max Act: 7.0696. Min Act: -0.1700
Data Index: 1663280 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19