Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1358 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2683. Min Range: -8.2683
Max Act: 8.2683. Min Act: -0.1699
Data Index: 8471085 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2683. Min Range: -8.2683
Max Act: 8.2058. Min Act: -0.1700
Data Index: 3797303 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.9558. Min Act: -0.1700
Data Index: 4621421 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.8933. Min Act: -0.1700
Data Index: 3907087 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.8308. Min Act: -0.1700
Data Index: 5948650 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.8308. Min Act: -0.1700
Data Index: 2791860 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7058. Min Act: -0.1700
Data Index: 1214089 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7683. Min Act: -0.1700
Data Index: 1205387 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7683. Min Act: -0.1700
Data Index: 4594390 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7683. Min Act: -0.1700
Data Index: 4034436 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7058. Min Act: -0.1700
Data Index: 1201817 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7058. Min Act: -0.1700
Data Index: 804574 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7683. Min Act: -0.1700
Data Index: 4629610 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7058. Min Act: -0.1700
Data Index: 4219258 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.7058. Min Act: -0.1700
Data Index: 8632830 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.6433. Min Act: -0.1700
Data Index: 4263495 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.6433. Min Act: -0.1700
Data Index: 6863649 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.6433. Min Act: -0.1700
Data Index: 5163814 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.6433. Min Act: -0.1700
Data Index: 5425127 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2683. Min Range: -8.2683
Max Act: 7.5808. Min Act: -0.1700
Data Index: 1166885 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19