Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0562. Min Range: -6.0562
Max Act: 6.0562. Min Act: -0.1700
Data Index: 7723099 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.9937. Min Act: -0.1700
Data Index: 814599 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.9937. Min Act: -0.1700
Data Index: 7422742 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.9625. Min Act: -0.1700
Data Index: 1760705 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8687. Min Act: -0.1700
Data Index: 5033027 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8375. Min Act: -0.1700
Data Index: 4832257 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8375. Min Act: -0.1700
Data Index: 8294598 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8062. Min Act: -0.1700
Data Index: 7930075 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8062. Min Act: -0.1700
Data Index: 2805060 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8062. Min Act: -0.1700
Data Index: 4730742 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.8062. Min Act: -0.1700
Data Index: 2174501 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7437. Min Act: -0.1700
Data Index: 737325 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7437. Min Act: -0.1700
Data Index: 3090134 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7437. Min Act: -0.1700
Data Index: 5097880 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7125. Min Act: -0.1700
Data Index: 164385 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7125. Min Act: -0.1700
Data Index: 211429 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7125. Min Act: -0.1700
Data Index: 8460096 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.7125. Min Act: -0.1700
Data Index: 2863029 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.6812. Min Act: -0.1700
Data Index: 7755317 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0562. Min Range: -6.0562
Max Act: 5.6812. Min Act: -0.1700
Data Index: 7725534 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19