Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5190 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2713. Min Range: -5.2713
Max Act: 5.2713. Min Act: -0.1700
Data Index: 8509956 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2713. Min Range: -5.2713
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2092135 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.9900. Min Act: -0.1700
Data Index: 1234126 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.9588. Min Act: -0.1700
Data Index: 1049575 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8963. Min Act: -0.1700
Data Index: 4104786 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8650. Min Act: -0.1700
Data Index: 3583335 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8650. Min Act: -0.1700
Data Index: 1344380 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8650. Min Act: -0.1700
Data Index: 7401543 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8650. Min Act: -0.1700
Data Index: 7745446 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8338. Min Act: -0.1700
Data Index: 2883528 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8338. Min Act: -0.1700
Data Index: 184038 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8338. Min Act: -0.1700
Data Index: 5692877 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8025. Min Act: -0.1700
Data Index: 5204950 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8025. Min Act: -0.1700
Data Index: 91798 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8025. Min Act: -0.1700
Data Index: 6997802 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.8025. Min Act: -0.1700
Data Index: 2059907 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.7088. Min Act: -0.1700
Data Index: 5204952 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.7400. Min Act: -0.1700
Data Index: 6409900 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.7400. Min Act: -0.1700
Data Index: 4762897 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2713. Min Range: -5.2713
Max Act: 4.7088. Min Act: -0.1700
Data Index: 7456075 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19