Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 714 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0351. Min Range: -5.0351
Max Act: 5.0351. Min Act: -0.1700
Data Index: 2774696 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0351. Min Range: -5.0351
Max Act: 5.0351. Min Act: -0.1700
Data Index: 2609999 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9726. Min Act: -0.1700
Data Index: 873689 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9101. Min Act: -0.1700
Data Index: 6334098 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9101. Min Act: -0.1700
Data Index: 4101798 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9101. Min Act: -0.1700
Data Index: 4758853 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9101. Min Act: -0.1700
Data Index: 7644726 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8476. Min Act: -0.1700
Data Index: 5468598 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8163. Min Act: -0.1700
Data Index: 7958279 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7851. Min Act: -0.1700
Data Index: 4401741 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7851. Min Act: -0.1700
Data Index: 8340500 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7538. Min Act: -0.1700
Data Index: 6408583 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7538. Min Act: -0.1700
Data Index: 3728412 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7538. Min Act: -0.1700
Data Index: 8722249 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6913. Min Act: -0.1700
Data Index: 4323050 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6913. Min Act: -0.1700
Data Index: 944393 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4533698 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 8197753 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6288. Min Act: -0.1700
Data Index: 4779195 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.5976. Min Act: -0.1700
Data Index: 7920700 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19