Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4125 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0490. Min Act: -0.1700
Data Index: 4440781 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0490. Min Act: -0.1700
Data Index: 2798251 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9552. Min Act: -0.1700
Data Index: 3218873 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8927. Min Act: -0.1700
Data Index: 3280579 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8927. Min Act: -0.1700
Data Index: 5632172 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.7990. Min Act: -0.1700
Data Index: 1563905 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.7365. Min Act: -0.1700
Data Index: 6296000 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.7052. Min Act: -0.1700
Data Index: 3997080 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.7052. Min Act: -0.1700
Data Index: 7604315 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.7052. Min Act: -0.1700
Data Index: 82268 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6740. Min Act: -0.1700
Data Index: 4285559 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6427. Min Act: -0.1700
Data Index: 1424452 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6740. Min Act: -0.1700
Data Index: 1396726 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6740. Min Act: -0.1700
Data Index: 1681614 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6427. Min Act: -0.1700
Data Index: 5479660 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6427. Min Act: -0.1700
Data Index: 5407280 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6115. Min Act: -0.1700
Data Index: 6354055 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7610777 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7494797 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.5802. Min Act: -0.1700
Data Index: 6271872 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19