Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2861. Min Range: -11.2861
Max Act: 11.2861. Min Act: -0.1700
Data Index: 7410451 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2861. Min Range: -11.2861
Max Act: 11.0986. Min Act: -0.1700
Data Index: 3868672 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2861. Min Range: -11.2861
Max Act: 11.0361. Min Act: -0.1700
Data Index: 3489758 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.8486. Min Act: -0.1700
Data Index: 4068126 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.7236. Min Act: -0.1700
Data Index: 1141364 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.7861. Min Act: -0.1700
Data Index: 3042691 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.6611. Min Act: -0.1700
Data Index: 7453690 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.5986. Min Act: -0.1700
Data Index: 2340213 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.5986. Min Act: -0.1700
Data Index: 1179611 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.5361. Min Act: -0.1700
Data Index: 3268564 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.4736. Min Act: -0.1700
Data Index: 4137788 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.4111. Min Act: -0.1700
Data Index: 7387284 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.2861. Min Act: -0.1700
Data Index: 629587 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 1460719 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 7027475 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.1611. Min Act: -0.1700
Data Index: 2177991 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 7617486 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 413824 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 3405431 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2861. Min Range: -11.2861
Max Act: 10.0986. Min Act: -0.1700
Data Index: 1486104 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19