Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5879 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.5048. Min Act: -0.1700
Data Index: 8251140 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3486. Min Act: -0.1700
Data Index: 6769468 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3173. Min Act: -0.1700
Data Index: 3379588 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3173. Min Act: -0.1700
Data Index: 8649846 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.2548. Min Act: -0.1700
Data Index: 4112167 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.1923. Min Act: -0.1700
Data Index: 5076378 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.1611. Min Act: -0.1700
Data Index: 6656040 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.1611. Min Act: -0.1700
Data Index: 698793 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.1611. Min Act: -0.1700
Data Index: 2827838 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0986. Min Act: -0.1700
Data Index: 4031525 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0986. Min Act: -0.1700
Data Index: 6016683 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0673. Min Act: -0.1700
Data Index: 4895773 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0673. Min Act: -0.1700
Data Index: 807389 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0361. Min Act: -0.1700
Data Index: 6891018 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0361. Min Act: -0.1700
Data Index: 2015745 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5048. Min Range: -5.5048
Max Act: 4.9736. Min Act: -0.1700
Data Index: 179843 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.0048. Min Act: -0.1700
Data Index: 6876825 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5048. Min Range: -5.5048
Max Act: 4.9736. Min Act: -0.1700
Data Index: 3844082 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5048. Min Range: -5.5048
Max Act: 4.9736. Min Act: -0.1700
Data Index: 2905867 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5048. Min Range: -5.5048
Max Act: 4.9736. Min Act: -0.1700
Data Index: 7448254 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19