Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.9074. Min Act: -0.1700
Data Index: 3753800 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.7823. Min Act: -0.1700
Data Index: 714100 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.7667. Min Act: -0.1700
Data Index: 710076 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.7354. Min Act: -0.1700
Data Index: 4258872 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.7198. Min Act: -0.1700
Data Index: 7078759 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1483152 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.6728. Min Act: -0.1700
Data Index: 1302611 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.6102. Min Act: -0.1700
Data Index: 5360514 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.6259. Min Act: -0.1700
Data Index: 7599387 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.6102. Min Act: -0.1700
Data Index: 4102739 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5946. Min Act: -0.1700
Data Index: 4859554 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.6102. Min Act: -0.1700
Data Index: 7642234 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5789. Min Act: -0.1700
Data Index: 4774478 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5789. Min Act: -0.1700
Data Index: 1968837 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5946. Min Act: -0.1700
Data Index: 53056 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5789. Min Act: -0.1700
Data Index: 6952747 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5476. Min Act: -0.1700
Data Index: 1959502 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5789. Min Act: -0.1700
Data Index: 2886221 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5476. Min Act: -0.1700
Data Index: 1046287 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9074. Min Range: -3.9074
Max Act: 3.5320. Min Act: -0.1700
Data Index: 2600467 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19