Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5089 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1502. Min Range: -3.1502
Max Act: 3.1502. Min Act: -0.1700
Data Index: 3694980 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.9925. Min Act: -0.1700
Data Index: 5448102 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8975. Min Act: -0.1700
Data Index: 3694982 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8499. Min Act: -0.1700
Data Index: 1703108 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8340. Min Act: -0.1700
Data Index: 3968039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8340. Min Act: -0.1700
Data Index: 4819853 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8181. Min Act: -0.1700
Data Index: 2676043 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8340. Min Act: -0.1700
Data Index: 1256144 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8340. Min Act: -0.1700
Data Index: 6307899 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8181. Min Act: -0.1700
Data Index: 7023872 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.8340. Min Act: -0.1700
Data Index: 8218057 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7703. Min Act: -0.1700
Data Index: 3753300 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7862. Min Act: -0.1700
Data Index: 4410687 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7703. Min Act: -0.1700
Data Index: 3304783 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7543. Min Act: -0.1700
Data Index: 2438908 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7543. Min Act: -0.1700
Data Index: 5613653 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7543. Min Act: -0.1700
Data Index: 1890188 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7384. Min Act: -0.1700
Data Index: 4088539 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7224. Min Act: -0.1700
Data Index: 5117162 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1502. Min Range: -3.1502
Max Act: 2.7224. Min Act: -0.1700
Data Index: 2418318 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19