Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.6472. Min Act: -0.1700
Data Index: 4412434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.6159. Min Act: -0.1700
Data Index: 2312491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5846. Min Act: -0.1700
Data Index: 4777114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5846. Min Act: -0.1700
Data Index: 6484377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8589972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 1042429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 2329240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 5341026 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 5407494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8472446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 2438011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 673831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 752777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 607998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5533. Min Act: -0.1700
Data Index: 6480858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1189704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5219. Min Act: -0.1700
Data Index: 5234796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5219. Min Act: -0.1700
Data Index: 4911239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1087401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6472. Min Range: -3.6472
Max Act: 3.5219. Min Act: -0.1700
Data Index: 4287041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19