Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2056 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.8724. Min Act: -0.1700
Data Index: 6136969 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.8412. Min Act: -0.1700
Data Index: 845665 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.6849. Min Act: -0.1700
Data Index: 477606 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.6849. Min Act: -0.1700
Data Index: 6075280 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.6537. Min Act: -0.1700
Data Index: 40483 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.6224. Min Act: -0.1700
Data Index: 47023 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.6224. Min Act: -0.1700
Data Index: 3550623 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5912. Min Act: -0.1700
Data Index: 6600177 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5912. Min Act: -0.1700
Data Index: 5643326 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5912. Min Act: -0.1700
Data Index: 5834604 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 8698778 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 5237935 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5912. Min Act: -0.1700
Data Index: 5173949 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 3655866 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 3419200 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 8335155 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1048067 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5287. Min Act: -0.1700
Data Index: 7385450 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2499326 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8724. Min Range: -5.8724
Max Act: 5.5599. Min Act: -0.1700
Data Index: 4997462 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19