Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1568. Min Range: -6.1568
Max Act: 6.1568. Min Act: -0.1700
Data Index: 364869 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1502039 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4491095 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4703859 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3630647 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.8443. Min Act: -0.1700
Data Index: 5736705 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.8130. Min Act: -0.1700
Data Index: 3688830 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.8130. Min Act: -0.1700
Data Index: 794781 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8067872 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.7505. Min Act: -0.1700
Data Index: 8782312 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2134084 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7630998 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.7193. Min Act: -0.1700
Data Index: 8507076 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3240829 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6880. Min Act: -0.1700
Data Index: 895417 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6880. Min Act: -0.1700
Data Index: 6016419 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6255. Min Act: -0.1700
Data Index: 97475 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6568. Min Act: -0.1700
Data Index: 8444726 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6568. Min Act: -0.1700
Data Index: 8233681 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1568. Min Range: -6.1568
Max Act: 5.6568. Min Act: -0.1700
Data Index: 8745841 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19