Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4614 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.8937. Min Act: -0.1700
Data Index: 1041618 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.8625. Min Act: -0.1700
Data Index: 1041637 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.3625. Min Act: -0.1700
Data Index: 5252668 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.3312. Min Act: -0.1700
Data Index: 1549536 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.3312. Min Act: -0.1700
Data Index: 6367775 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.3312. Min Act: -0.1700
Data Index: 6718029 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.1750. Min Act: -0.1700
Data Index: 5102127 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.1750. Min Act: -0.1700
Data Index: 119411 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.1437. Min Act: -0.1700
Data Index: 305336 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.1125. Min Act: -0.1700
Data Index: 867251 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.0812. Min Act: -0.1700
Data Index: 842202 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.0500. Min Act: -0.1700
Data Index: 106679 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6483798 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8937. Min Range: -5.8937
Max Act: 5.0187. Min Act: -0.1700
Data Index: 123294 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9875. Min Act: -0.1700
Data Index: 744494 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9875. Min Act: -0.1700
Data Index: 8822975 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9562. Min Act: -0.1700
Data Index: 1041639 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9875. Min Act: -0.1700
Data Index: 2461197 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9562. Min Act: -0.1700
Data Index: 589123 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8937. Min Range: -5.8937
Max Act: 4.9562. Min Act: -0.1700
Data Index: 5433636 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19