Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.9716. Min Act: -0.1700
Data Index: 3064463 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.8778. Min Act: -0.1700
Data Index: 5983295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.8153. Min Act: -0.1700
Data Index: 7884522 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.7214. Min Act: -0.1700
Data Index: 365322 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.7058. Min Act: -0.1700
Data Index: 6936687 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.6432. Min Act: -0.1700
Data Index: 7493484 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.6589. Min Act: -0.1700
Data Index: 6760080 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.6432. Min Act: -0.1700
Data Index: 392883 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5806. Min Act: -0.1700
Data Index: 4872722 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5493. Min Act: -0.1700
Data Index: 1138666 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5493. Min Act: -0.1700
Data Index: 2249014 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5493. Min Act: -0.1700
Data Index: 1289870 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5493. Min Act: -0.1700
Data Index: 6212889 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5337. Min Act: -0.1700
Data Index: 7208425 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5337. Min Act: -0.1700
Data Index: 2795292 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5337. Min Act: -0.1700
Data Index: 7197037 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5180. Min Act: -0.1700
Data Index: 3414680 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5180. Min Act: -0.1700
Data Index: 5858344 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5180. Min Act: -0.1700
Data Index: 6346840 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9716. Min Range: -3.9716
Max Act: 3.5180. Min Act: -0.1700
Data Index: 1191364 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19