Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 1248251 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 8765318 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 1602498 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.5828. Min Act: -0.1700
Data Index: 4307246 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.5828. Min Act: -0.1700
Data Index: 8410996 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.5828. Min Act: -0.1700
Data Index: 4522458 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.5203. Min Act: -0.1700
Data Index: 6382736 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.5203. Min Act: -0.1700
Data Index: 3138552 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3953. Min Act: -0.1700
Data Index: 4328000 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3953. Min Act: -0.1700
Data Index: 2745892 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3953. Min Act: -0.1700
Data Index: 6129309 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3328. Min Act: -0.1700
Data Index: 8668293 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3953. Min Act: -0.1700
Data Index: 6651597 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3328. Min Act: -0.1700
Data Index: 7473056 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3953. Min Act: -0.1700
Data Index: 6689818 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3328. Min Act: -0.1700
Data Index: 2699146 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3328. Min Act: -0.1700
Data Index: 6370171 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.3328. Min Act: -0.1700
Data Index: 6326448 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.2703. Min Act: -0.1700
Data Index: 1026286 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6453. Min Range: -8.6453
Max Act: 8.2703. Min Act: -0.1700
Data Index: 3927021 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19