Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.5986. Min Act: -0.1700
Data Index: 4048244 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.4736. Min Act: -0.1700
Data Index: 3014439 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.3798. Min Act: -0.1700
Data Index: 3401953 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.2861. Min Act: -0.1700
Data Index: 5498885 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.2548. Min Act: -0.1700
Data Index: 7489111 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.2861. Min Act: -0.1700
Data Index: 6571373 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.1611. Min Act: -0.1700
Data Index: 1361328 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.0673. Min Act: -0.1700
Data Index: 3076127 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.0673. Min Act: -0.1700
Data Index: 4346866 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.0048. Min Act: -0.1700
Data Index: 4409127 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5986. Min Range: -6.5986
Max Act: 6.0048. Min Act: -0.1700
Data Index: 8273535 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.9423. Min Act: -0.1700
Data Index: 7891618 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.9423. Min Act: -0.1700
Data Index: 2109770 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8798. Min Act: -0.1700
Data Index: 3032571 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8798. Min Act: -0.1700
Data Index: 5719310 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8798. Min Act: -0.1700
Data Index: 8051206 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8486. Min Act: -0.1700
Data Index: 2092141 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.7861. Min Act: -0.1700
Data Index: 3721642 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8173. Min Act: -0.1700
Data Index: 7192754 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5986. Min Range: -6.5986
Max Act: 5.8486. Min Act: -0.1700
Data Index: 1380755 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19