Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4710. Min Range: -9.4710
Max Act: 9.4710. Min Act: -0.1700
Data Index: 3512441 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.7210. Min Act: -0.1700
Data Index: 3264864 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.7835. Min Act: -0.1700
Data Index: 5490775 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.6585. Min Act: -0.1700
Data Index: 3689458 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.5960. Min Act: -0.1700
Data Index: 8076146 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.5335. Min Act: -0.1700
Data Index: 2224901 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.5335. Min Act: -0.1700
Data Index: 4058426 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.5335. Min Act: -0.1700
Data Index: 3188891 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.5335. Min Act: -0.1700
Data Index: 6321574 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4710. Min Act: -0.1700
Data Index: 6380392 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4710. Min Act: -0.1700
Data Index: 6512817 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4710. Min Act: -0.1700
Data Index: 150188 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4710. Min Act: -0.1700
Data Index: 3667528 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 7496940 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 860353 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 1000896 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 4223055 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 4411063 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.4085. Min Act: -0.1700
Data Index: 8308270 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4710. Min Range: -9.4710
Max Act: 8.2835. Min Act: -0.1700
Data Index: 4489558 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19