Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0256. Min Range: -4.0256
Max Act: 4.0256. Min Act: -0.1700
Data Index: 8334462 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.9318. Min Act: -0.1700
Data Index: 1454936 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.9006. Min Act: -0.1700
Data Index: 3076553 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.8068. Min Act: -0.1700
Data Index: 4124346 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.8068. Min Act: -0.1700
Data Index: 6933687 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.7755. Min Act: -0.1700
Data Index: 7848472 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.7442. Min Act: -0.1700
Data Index: 8248473 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.7286. Min Act: -0.1700
Data Index: 7760716 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5044035 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1197770 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 8413088 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 7480113 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1158803 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 7244009 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6660. Min Act: -0.1700
Data Index: 651834 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6504. Min Act: -0.1700
Data Index: 509903 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6504. Min Act: -0.1700
Data Index: 3107172 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1539415 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6660. Min Act: -0.1700
Data Index: 5031004 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0256. Min Range: -4.0256
Max Act: 3.6504. Min Act: -0.1700
Data Index: 1737768 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19