Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1289 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0482. Min Range: -5.0482
Max Act: 5.0482. Min Act: -0.1700
Data Index: 5123408 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0482. Min Range: -5.0482
Max Act: 5.0170. Min Act: -0.1700
Data Index: 231441 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0482. Min Range: -5.0482
Max Act: 5.0170. Min Act: -0.1700
Data Index: 5605687 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9857. Min Act: -0.1700
Data Index: 949317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9857. Min Act: -0.1700
Data Index: 3903355 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6081709 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9545. Min Act: -0.1700
Data Index: 8451588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9545. Min Act: -0.1700
Data Index: 4544470 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9545. Min Act: -0.1700
Data Index: 2622197 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9545. Min Act: -0.1700
Data Index: 7404779 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9545. Min Act: -0.1700
Data Index: 417838 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 5625565 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4050461 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.8920. Min Act: -0.1700
Data Index: 8568202 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 2863694 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1677
Data Index: 6943881 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 1549688 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6389740 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 1316231 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0482. Min Range: -5.0482
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4197909 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19