Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.5724. Min Act: -0.1700
Data Index: 2094697 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.3536. Min Act: -0.1698
Data Index: 5176258 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.2286. Min Act: -0.1700
Data Index: 4574428 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1700
Data Index: 4257569 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.2286. Min Act: -0.1700
Data Index: 5498723 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1661. Min Act: -0.1700
Data Index: 6305867 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.2599. Min Act: -0.1700
Data Index: 1725788 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.2911. Min Act: -0.1700
Data Index: 4472350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1699
Data Index: 2486086 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1697
Data Index: 8821200 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1974. Min Act: -0.1700
Data Index: 5097845 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1036. Min Act: -0.1700
Data Index: 8057598 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1661. Min Act: -0.1685
Data Index: 5938439 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1036. Min Act: -0.1700
Data Index: 7953835 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0724. Min Act: -0.1699
Data Index: 3637477 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1036. Min Act: -0.1700
Data Index: 7487782 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1700
Data Index: 7401099 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1661. Min Act: -0.1700
Data Index: 2609167 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0411. Min Act: -0.1700
Data Index: 6062588 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2490918 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19