Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.7616. Min Act: -0.1700
Data Index: 5310500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.7616. Min Act: -0.1700
Data Index: 4457503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.7616. Min Act: -0.1700
Data Index: 2795261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.6991. Min Act: -0.1700
Data Index: 6105572 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2269767 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.6053. Min Act: -0.1700
Data Index: 2630896 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5741. Min Act: -0.1700
Data Index: 4385911 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5116. Min Act: -0.1700
Data Index: 8824300 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5741. Min Act: -0.1700
Data Index: 2269757 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5428. Min Act: -0.1700
Data Index: 3112723 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5428. Min Act: -0.1700
Data Index: 7969178 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5116. Min Act: -0.1700
Data Index: 6823717 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.5116. Min Act: -0.1700
Data Index: 8237226 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4803. Min Act: -0.1700
Data Index: 6174393 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4803. Min Act: -0.1700
Data Index: 347202 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4803. Min Act: -0.1700
Data Index: 4817148 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4803. Min Act: -0.1700
Data Index: 2762999 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4178. Min Act: -0.1700
Data Index: 4385909 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 347203 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7616. Min Range: -5.7616
Max Act: 5.4491. Min Act: -0.1700
Data Index: 7819777 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19