Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 268 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.6498. Min Act: -0.1700
Data Index: 5316072 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1796344 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.1810. Min Act: -0.1700
Data Index: 5151609 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.1185. Min Act: -0.1700
Data Index: 5151605 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.0873. Min Act: -0.1700
Data Index: 7334724 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.0873. Min Act: -0.1700
Data Index: 4754940 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.0560. Min Act: -0.1700
Data Index: 1196300 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.0560. Min Act: -0.1700
Data Index: 5051000 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6498. Min Range: -6.6498
Max Act: 6.0248. Min Act: -0.1700
Data Index: 4271557 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1952658 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9935. Min Act: -0.1700
Data Index: 680126 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9623. Min Act: -0.1700
Data Index: 2653072 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6614057 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9310. Min Act: -0.1700
Data Index: 6651307 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.9310. Min Act: -0.1700
Data Index: 5941927 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.8998. Min Act: -0.1700
Data Index: 4453914 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.8685. Min Act: -0.1700
Data Index: 7118762 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.8685. Min Act: -0.1700
Data Index: 3706530 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.8685. Min Act: -0.1700
Data Index: 8025900 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6498. Min Range: -6.6498
Max Act: 5.8998. Min Act: -0.1700
Data Index: 756835 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19