Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.7713. Min Act: -0.1700
Data Index: 6229881 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.7713. Min Act: -0.1700
Data Index: 207820 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.7088. Min Act: -0.1700
Data Index: 1157997 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.6463. Min Act: -0.1700
Data Index: 4954504 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.6151. Min Act: -0.1700
Data Index: 42256 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.6151. Min Act: -0.1700
Data Index: 4954514 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.6463. Min Act: -0.1700
Data Index: 7174861 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.2401. Min Act: -0.1700
Data Index: 7601580 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.1463. Min Act: -0.1700
Data Index: 5092560 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.0526. Min Act: -0.1700
Data Index: 8441966 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7713. Min Range: -7.7713
Max Act: 7.0526. Min Act: -0.1700
Data Index: 6655922 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8963. Min Act: -0.1700
Data Index: 1418369 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8651. Min Act: -0.1700
Data Index: 6042380 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8963. Min Act: -0.1700
Data Index: 6954810 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8651. Min Act: -0.1700
Data Index: 998727 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8651. Min Act: -0.1700
Data Index: 1509185 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8338. Min Act: -0.1700
Data Index: 536590 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8338. Min Act: -0.1700
Data Index: 7918762 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.8338. Min Act: -0.1700
Data Index: 8237303 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7713. Min Range: -7.7713
Max Act: 6.7713. Min Act: -0.1700
Data Index: 1817865 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19