Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8106. Min Range: -11.8106
Max Act: 11.8106. Min Act: -0.1700
Data Index: 3903814 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8106. Min Range: -11.8106
Max Act: 11.1856. Min Act: -0.1700
Data Index: 3560478 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8106. Min Range: -11.8106
Max Act: 11.0606. Min Act: -0.1700
Data Index: 8164946 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8106. Min Range: -11.8106
Max Act: 11.0606. Min Act: -0.1700
Data Index: 4027848 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.8106. Min Act: -0.1700
Data Index: 6350212 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.6856. Min Act: -0.1700
Data Index: 4498965 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.4981. Min Act: -0.1700
Data Index: 2171554 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.4356. Min Act: -0.1700
Data Index: 1780515 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.2481. Min Act: -0.1700
Data Index: 3254910 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.2481. Min Act: -0.1700
Data Index: 6845073 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.1856. Min Act: -0.1700
Data Index: 7551344 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8106. Min Range: -11.8106
Max Act: 10.1231. Min Act: -0.1700
Data Index: 4903751 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.9981. Min Act: -0.1700
Data Index: 2525432 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.9981. Min Act: -0.1700
Data Index: 4283903 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.8731. Min Act: -0.1700
Data Index: 1335552 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.8106. Min Act: -0.1700
Data Index: 4716805 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.8731. Min Act: -0.1700
Data Index: 4007180 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.7481. Min Act: -0.1700
Data Index: 2330707 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.7481. Min Act: -0.1700
Data Index: 617697 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8106. Min Range: -11.8106
Max Act: 9.8106. Min Act: -0.1700
Data Index: 1729153 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19