Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5421 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.5826. Min Act: -0.1700
Data Index: 3055735 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.5826. Min Act: -0.1700
Data Index: 7309665 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.5201. Min Act: -0.1700
Data Index: 3383452 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.5201. Min Act: -0.1700
Data Index: 6545536 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.3951. Min Act: -0.1700
Data Index: 7322776 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.3951. Min Act: -0.1700
Data Index: 5595360 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.3326. Min Act: -0.1700
Data Index: 1544723 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.3326. Min Act: -0.1700
Data Index: 7394582 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.3326. Min Act: -0.1700
Data Index: 5059112 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2701. Min Act: -0.1700
Data Index: 1639562 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2701. Min Act: -0.1700
Data Index: 6930614 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 1449431 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 6908915 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2701. Min Act: -0.1700
Data Index: 6633171 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 5793219 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 3548445 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 4355897 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.2076. Min Act: -0.1700
Data Index: 4296521 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.1451. Min Act: -0.1700
Data Index: 862043 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5826. Min Range: -8.5826
Max Act: 8.1451. Min Act: -0.1700
Data Index: 6890109 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19