Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5298. Min Range: -8.5298
Max Act: 8.5298. Min Act: -0.1700
Data Index: 3762970 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5298. Min Range: -8.5298
Max Act: 8.4673. Min Act: -0.1700
Data Index: 119135 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5298. Min Range: -8.5298
Max Act: 8.1236. Min Act: -0.1700
Data Index: 188542 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.9361. Min Act: -0.1700
Data Index: 5365765 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.8423. Min Act: -0.1700
Data Index: 4045624 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.8736. Min Act: -0.1700
Data Index: 7468370 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.7798. Min Act: -0.1700
Data Index: 3159934 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.7486. Min Act: -0.1700
Data Index: 960599 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.7173. Min Act: -0.1700
Data Index: 3159929 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.6548. Min Act: -0.1700
Data Index: 4258446 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.5923. Min Act: -0.1700
Data Index: 2202988 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.5611. Min Act: -0.1700
Data Index: 2653182 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.4361. Min Act: -0.1700
Data Index: 4910891 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.4673. Min Act: -0.1700
Data Index: 2623211 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.4048. Min Act: -0.1700
Data Index: 4045623 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.3423. Min Act: -0.1700
Data Index: 2221134 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.3423. Min Act: -0.1700
Data Index: 8165310 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.3423. Min Act: -0.1700
Data Index: 1081658 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.2798. Min Act: -0.1700
Data Index: 469608 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5298. Min Range: -8.5298
Max Act: 7.2486. Min Act: -0.1700
Data Index: 3646993 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19