Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4928 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0610. Min Range: -5.0610
Max Act: 5.0610. Min Act: -0.1700
Data Index: 5590076 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9985. Min Act: -0.1700
Data Index: 2136895 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9985. Min Act: -0.1700
Data Index: 6729770 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9985. Min Act: -0.1700
Data Index: 5421159 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9985. Min Act: -0.1700
Data Index: 8746024 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9672. Min Act: -0.1700
Data Index: 3203361 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9672. Min Act: -0.1700
Data Index: 7964567 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9672. Min Act: -0.1700
Data Index: 658873 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9360. Min Act: -0.1700
Data Index: 7812005 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9360. Min Act: -0.1700
Data Index: 6165574 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9047. Min Act: -0.1700
Data Index: 3469506 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9360. Min Act: -0.1700
Data Index: 7096014 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9360. Min Act: -0.1700
Data Index: 8047710 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8735. Min Act: -0.1700
Data Index: 333891 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8735. Min Act: -0.1700
Data Index: 1466100 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.9047. Min Act: -0.1700
Data Index: 6354610 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8735. Min Act: -0.1700
Data Index: 1494503 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8735. Min Act: -0.1700
Data Index: 436422 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8422. Min Act: -0.1700
Data Index: 4573129 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0610. Min Range: -5.0610
Max Act: 4.8422. Min Act: -0.1700
Data Index: 1325312 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19