Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.2550. Min Act: -0.1700
Data Index: 8646286 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.2550. Min Act: -0.1700
Data Index: 7142448 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.1925. Min Act: -0.1700
Data Index: 2619901 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.0988. Min Act: -0.1700
Data Index: 906754 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.0675. Min Act: -0.1700
Data Index: 7222038 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.0363. Min Act: -0.1700
Data Index: 1804361 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2550. Min Range: -8.2550
Max Act: 8.0675. Min Act: -0.1700
Data Index: 2174501 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.9425. Min Act: -0.1700
Data Index: 6771563 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.9425. Min Act: -0.1700
Data Index: 6529286 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.8800. Min Act: -0.1700
Data Index: 5440946 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.8488. Min Act: -0.1700
Data Index: 4957979 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.7863. Min Act: -0.1700
Data Index: 8093009 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.7550. Min Act: -0.1700
Data Index: 7396654 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.7863. Min Act: -0.1700
Data Index: 8824100 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.6925. Min Act: -0.1700
Data Index: 7252981 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.6613. Min Act: -0.1700
Data Index: 5147417 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.5988. Min Act: -0.1700
Data Index: 984096 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.5988. Min Act: -0.1700
Data Index: 3207828 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.5675. Min Act: -0.1700
Data Index: 246048 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2550. Min Range: -8.2550
Max Act: 7.5675. Min Act: -0.1700
Data Index: 3051733 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19