Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5094 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1002. Min Range: -2.1002
Max Act: 2.1002. Min Act: -0.1700
Data Index: 7822465 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1002. Min Range: -2.1002
Max Act: 2.0330. Min Act: -0.1700
Data Index: 4346280 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1002. Min Range: -2.1002
Max Act: 2.0161. Min Act: -0.1700
Data Index: 4837877 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9823. Min Act: -0.1700
Data Index: 4676813 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9992. Min Act: -0.1700
Data Index: 8657191 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9654. Min Act: -0.1700
Data Index: 836716 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9654. Min Act: -0.1700
Data Index: 3742884 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9654. Min Act: -0.1700
Data Index: 8072856 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9654. Min Act: -0.1700
Data Index: 8718066 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 7698127 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 7493591 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9314. Min Act: -0.1700
Data Index: 1409151 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 7233780 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 3113823 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 7196305 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 5653852 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 1196812 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9314. Min Act: -0.1700
Data Index: 7027577 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9484. Min Act: -0.1700
Data Index: 4334851 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1002. Min Range: -2.1002
Max Act: 1.9314. Min Act: -0.1700
Data Index: 7994915 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19