Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6716. Min Act: -0.1700
Data Index: 914422 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 3061133 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 4120391 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 4204714 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5921032 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 7981555 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5979787 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 275379 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 7544090 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 8446741 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 8371637 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 7812325 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2176990 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 5977397 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 451008 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6090. Min Act: -0.1700
Data Index: 3772673 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.6403. Min Act: -0.1700
Data Index: 3598919 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.5777. Min Act: -0.1700
Data Index: 2999561 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.5777. Min Act: -0.1700
Data Index: 334591 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6716. Min Range: -3.6716
Max Act: 3.5777. Min Act: -0.1700
Data Index: 675628 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19