Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.8525. Min Act: -0.1700
Data Index: 6927154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6961. Min Act: -0.1700
Data Index: 5573763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6648. Min Act: -0.1700
Data Index: 1141544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6648. Min Act: -0.1700
Data Index: 862333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6648. Min Act: -0.1700
Data Index: 3915095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6335. Min Act: -0.1700
Data Index: 6484550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6335. Min Act: -0.1700
Data Index: 262917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6022. Min Act: -0.1700
Data Index: 6869253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6022. Min Act: -0.1700
Data Index: 2527937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6022. Min Act: -0.1700
Data Index: 8564216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5709. Min Act: -0.1700
Data Index: 933247 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6022. Min Act: -0.1700
Data Index: 3079284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5396. Min Act: -0.1700
Data Index: 4404598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5709. Min Act: -0.1700
Data Index: 7189626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5709. Min Act: -0.1700
Data Index: 1100197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5709. Min Act: -0.1700
Data Index: 1450779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5709. Min Act: -0.1700
Data Index: 69948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5396. Min Act: -0.1700
Data Index: 4533939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5396. Min Act: -0.1700
Data Index: 2519057 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.5396. Min Act: -0.1700
Data Index: 2557921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19