Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1213 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0620. Min Range: -2.0620
Max Act: 2.0620. Min Act: -0.1700
Data Index: 1439895 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9777. Min Act: -0.1700
Data Index: 7747802 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9777. Min Act: -0.1700
Data Index: 3518973 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9777. Min Act: -0.1700
Data Index: 771965 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9438. Min Act: -0.1700
Data Index: 5008765 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9268. Min Act: -0.1700
Data Index: 8279433 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9438. Min Act: -0.1700
Data Index: 12260 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9268. Min Act: -0.1700
Data Index: 3008846 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9268. Min Act: -0.1700
Data Index: 2469581 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9268. Min Act: -0.1700
Data Index: 472323 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9268. Min Act: -0.1700
Data Index: 5727600 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9097. Min Act: -0.1700
Data Index: 2473534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.8927. Min Act: -0.1700
Data Index: 8141038 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9012. Min Act: -0.1700
Data Index: 3224002 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9012. Min Act: -0.1700
Data Index: 3599736 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9012. Min Act: -0.1700
Data Index: 602923 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.9012. Min Act: -0.1700
Data Index: 4352042 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.8841. Min Act: -0.1700
Data Index: 4530996 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.8927. Min Act: -0.1700
Data Index: 8774153 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0620. Min Range: -2.0620
Max Act: 1.8927. Min Act: -0.1700
Data Index: 6324544 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19