Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 4672501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 2018573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 2071996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 5973944 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 5935030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9729. Min Act: -0.1700
Data Index: 7639834 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9416. Min Act: -0.1700
Data Index: 3605192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9416. Min Act: -0.1700
Data Index: 5243004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9416. Min Act: -0.1700
Data Index: 6316948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9416. Min Act: -0.1700
Data Index: 6662849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 3088246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 1345329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 4312163 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 6751405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 4894804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 235908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 5553081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 7002645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 6588013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9729. Min Range: -3.9729
Max Act: 3.9104. Min Act: -0.1700
Data Index: 5123427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19