Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.4641. Min Act: -0.1700
Data Index: 5737279 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.4328. Min Act: -0.1700
Data Index: 6784031 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3391. Min Act: -0.1700
Data Index: 3729641 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3391. Min Act: -0.1700
Data Index: 7309823 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6771557 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3078. Min Act: -0.1700
Data Index: 660921 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6878068 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3078. Min Act: -0.1700
Data Index: 7309826 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2766. Min Act: -0.1700
Data Index: 5799238 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2766. Min Act: -0.1700
Data Index: 7470616 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2141. Min Act: -0.1700
Data Index: 2589177 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 3344932 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 5726860 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 8438981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 5287991 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 467507 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 1042057 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2453. Min Act: -0.1700
Data Index: 1029237 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1828. Min Act: -0.1700
Data Index: 1210322 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.2141. Min Act: -0.1700
Data Index: 3083960 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19